https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&feed=atom&action=history
机器学习 Machine Learning - 版本历史
2024-03-28T11:19:16Z
本wiki的该页面的版本历史
MediaWiki 1.35.0
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=28336&oldid=prev
薄荷:/* 局限 */
2022-01-07T12:15:10Z
<p><span dir="auto"><span class="autocomment">局限</span></span></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2022年1月7日 (五) 12:15的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l383" >第383行:</td>
<td colspan="2" class="diff-lineno">第383行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>机器学习方法尤其会受到不同数据偏见的影响。只针对当前客户进行训练的机器学习系统可能无法预测训练数据中未表示的新客户组的需求。当接受人工数据训练时,机器学习很可能会产生与社会上已经存在的相同的成体制偏见和无意识偏见<ref>{{Cite journal|last=Garcia|first=Megan|date=2016|title=Racist in the Machine|url=https://read.dukeupress.edu/world-policy-journal/article/33/4/111-117/30942|journal=World Policy Journal|language=en|volume=33|issue=4|pages=111–117<del class="diffchange diffchange-inline">|issn:0740-2775</del>}}</ref> 。</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>机器学习方法尤其会受到不同数据偏见的影响。只针对当前客户进行训练的机器学习系统可能无法预测训练数据中未表示的新客户组的需求。当接受人工数据训练时,机器学习很可能会产生与社会上已经存在的相同的成体制偏见和无意识偏见<ref>{{Cite journal|last=Garcia|first=Megan|date=2016|title=Racist in the Machine|url=https://read.dukeupress.edu/world-policy-journal/article/33/4/111-117/30942|journal=World Policy Journal|language=en|volume=33|issue=4|pages=111–117}}</ref> 。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>从数据中学到的语言模型已被证明含有类似人类的偏见<ref>{{Cite journal|last=Caliskan|first=Aylin|last2=Bryson|first2=Joanna J.|last3=Narayanan|first3=Arvind|date=2017-04-14|title=Semantics derived automatically from language corpora contain human-like biases|url=http://science.sciencemag.org/content/356/6334/183|journal=Science|language=en|volume=356|issue=6334|pages=183–186}}</ref><ref>Wang, Xinan; Dasgupta, Sanjoy (2016), Lee, D. D.; Sugiyama, M.; Luxburg, U. V.; Guyon, I., eds., [http://papers.nips.cc/paper/6227-an-algorithm-for-l1-nearest-neighbor-search-via-monotonic-embedding.pdf "An algorithm for L1 nearest neighbor search via monotonic embedding"] (PDF), ''Advances in Neural Information Processing Systems 29'', Curran Associates, Inc., pp. 983–991, Retrieved 2018-08-20</ref> 。用于犯罪风险评估的机器学习系统被发现对黑人有偏见<ref>[https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing "Machine Bias"]. ProPublica. Julia Angwin, Jeff Larson, Lauren Kirchner, Surya Mattu. 2016-05-23. Retrieved 2018-08-20.</ref><ref>[https://www.nytimes.com/2017/10/26/opinion/algorithm-compas-sentencing-bias.html "Opinion | When an Algorithm Helps Send You to Prison"]. New York Times. Retrieved 2018-08-20.</ref> 。在2015年,谷歌上黑人的照片常常被贴上大猩猩的标签<ref>[https://www.bbc.co.uk/news/technology-33347866 "Google apologises for racist blunder"]. BBC News. 2015-07-01. Retrieved 2018-08-20.</ref> ,而到2018年,这仍然没有得到很好的解决,但据报道,谷歌仍在使用变通方法将所有大猩猩从训练数据中删除,因此根本无法识别真正的大猩猩<ref>[https://www.theverge.com/2018/1/12/16882408/google-racist-gorillas-photo-recognition-algorithm-ai "Google 'fixed' its racist algorithm by removing gorillas from its image-labeling tech"]. The Verge. Retrieved 2018-08-20.</ref>。在许多其他系统中<ref>[https://www.nytimes.com/2016/06/26/opinion/sunday/artificial-intelligences-white-guy-problem.html "Opinion | Artificial Intelligence's White Guy Problem"]. New York Times. Retrieved 2018-08-20.</ref> ,也发现了识别非白人的类似问题。2016年,微软测试了一个从Twitter上学习的[https://en.wikipedia.org/wiki/Chatbot 聊天机器人],而后者却很快学会了种族主义和性别歧视的语言<ref>Metz, Rachel. [https://www.technologyreview.com/s/601111/why-microsoft-accidentally-unleashed-a-neo-nazi-sexbot/ "Why Microsoft's teen chatbot, Tay, said lots of awful things online"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。由于这些挑战,机器在其他领域的有效使用仍有很长的路要走<ref>Simonite, Tom. [https://www.technologyreview.com/s/603944/microsoft-ai-isnt-yet-adaptable-enough-to-help-businesses/ "Microsoft says its racist chatbot illustrates how AI isn't adaptable enough to help most businesses"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。2018年,[https://en.wikipedia.org/wiki/Uber Uber]的一辆自动驾驶汽车未能检测到行人并导致其在事故中丧生。<ref>[https://www.economist.com/the-economist-explains/2018/05/29/why-ubers-self-driving-car-killed-a-pedestrian "Why Uber's self-driving car killed a pedestrian"]. The Economist. Retrieved 2018-08-20.</ref>。IBM Watson系统在医疗保健领域使用机器学习的尝试,即便经过多年的时间和数十亿美元的投资,也未能实现<ref></div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>从数据中学到的语言模型已被证明含有类似人类的偏见<ref>{{Cite journal|last=Caliskan|first=Aylin|last2=Bryson|first2=Joanna J.|last3=Narayanan|first3=Arvind|date=2017-04-14|title=Semantics derived automatically from language corpora contain human-like biases|url=http://science.sciencemag.org/content/356/6334/183|journal=Science|language=en|volume=356|issue=6334|pages=183–186}}</ref><ref>Wang, Xinan; Dasgupta, Sanjoy (2016), Lee, D. D.; Sugiyama, M.; Luxburg, U. V.; Guyon, I., eds., [http://papers.nips.cc/paper/6227-an-algorithm-for-l1-nearest-neighbor-search-via-monotonic-embedding.pdf "An algorithm for L1 nearest neighbor search via monotonic embedding"] (PDF), ''Advances in Neural Information Processing Systems 29'', Curran Associates, Inc., pp. 983–991, Retrieved 2018-08-20</ref> 。用于犯罪风险评估的机器学习系统被发现对黑人有偏见<ref>[https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing "Machine Bias"]. ProPublica. Julia Angwin, Jeff Larson, Lauren Kirchner, Surya Mattu. 2016-05-23. Retrieved 2018-08-20.</ref><ref>[https://www.nytimes.com/2017/10/26/opinion/algorithm-compas-sentencing-bias.html "Opinion | When an Algorithm Helps Send You to Prison"]. New York Times. Retrieved 2018-08-20.</ref> 。在2015年,谷歌上黑人的照片常常被贴上大猩猩的标签<ref>[https://www.bbc.co.uk/news/technology-33347866 "Google apologises for racist blunder"]. BBC News. 2015-07-01. Retrieved 2018-08-20.</ref> ,而到2018年,这仍然没有得到很好的解决,但据报道,谷歌仍在使用变通方法将所有大猩猩从训练数据中删除,因此根本无法识别真正的大猩猩<ref>[https://www.theverge.com/2018/1/12/16882408/google-racist-gorillas-photo-recognition-algorithm-ai "Google 'fixed' its racist algorithm by removing gorillas from its image-labeling tech"]. The Verge. Retrieved 2018-08-20.</ref>。在许多其他系统中<ref>[https://www.nytimes.com/2016/06/26/opinion/sunday/artificial-intelligences-white-guy-problem.html "Opinion | Artificial Intelligence's White Guy Problem"]. New York Times. Retrieved 2018-08-20.</ref> ,也发现了识别非白人的类似问题。2016年,微软测试了一个从Twitter上学习的[https://en.wikipedia.org/wiki/Chatbot 聊天机器人],而后者却很快学会了种族主义和性别歧视的语言<ref>Metz, Rachel. [https://www.technologyreview.com/s/601111/why-microsoft-accidentally-unleashed-a-neo-nazi-sexbot/ "Why Microsoft's teen chatbot, Tay, said lots of awful things online"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。由于这些挑战,机器在其他领域的有效使用仍有很长的路要走<ref>Simonite, Tom. [https://www.technologyreview.com/s/603944/microsoft-ai-isnt-yet-adaptable-enough-to-help-businesses/ "Microsoft says its racist chatbot illustrates how AI isn't adaptable enough to help most businesses"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。2018年,[https://en.wikipedia.org/wiki/Uber Uber]的一辆自动驾驶汽车未能检测到行人并导致其在事故中丧生。<ref>[https://www.economist.com/the-economist-explains/2018/05/29/why-ubers-self-driving-car-killed-a-pedestrian "Why Uber's self-driving car killed a pedestrian"]. The Economist. Retrieved 2018-08-20.</ref>。IBM Watson系统在医疗保健领域使用机器学习的尝试,即便经过多年的时间和数十亿美元的投资,也未能实现<ref></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[https://www.statnews.com/2018/07/25/ibm-watson-recommended-unsafe-incorrect-treatments/ "IBM's Watson recommended 'unsafe and incorrect' cancer treatments - STAT"]. STAT. 2018-07-25. Retrieved 2018-08-21.</ref><ref>Hernandez, Daniela; Greenwald, Ted (2018-08-11). [https://www.wsj.com/articles/ibm-bet-billions-that-watson-could-improve-cancer-treatment-it-hasnt-worked-1533961147 "IBM Has a Watson Dilemma"].Wall Street Journal. ISSN 0099-9660. Retrieved 2018-08-21.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[https://www.statnews.com/2018/07/25/ibm-watson-recommended-unsafe-incorrect-treatments/ "IBM's Watson recommended 'unsafe and incorrect' cancer treatments - STAT"]. STAT. 2018-07-25. Retrieved 2018-08-21.</ref><ref>Hernandez, Daniela; Greenwald, Ted (2018-08-11). [https://www.wsj.com/articles/ibm-bet-billions-that-watson-could-improve-cancer-treatment-it-hasnt-worked-1533961147 "IBM Has a Watson Dilemma"].Wall Street Journal. ISSN 0099-9660. Retrieved 2018-08-21.</div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=28335&oldid=prev
2022年1月7日 (五) 12:14 薄荷
2022-01-07T12:14:37Z
<p></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2022年1月7日 (五) 12:14的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l55" >第55行:</td>
<td colspan="2" class="diff-lineno">第55行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>机器学习,作为一个独立的领域,在20世纪90年代开始蓬勃发展。机器学习的目标从实现人工智能转变为解决可解决的实践性问题。它将重点从AI中继承的符号方法转向了来自于统计学和概率论的方法和模型<ref name="changing" /> ,同时也受益于数字化信息日益增长的普及性,以及互联网传播信息的能力。</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>机器学习,作为一个独立的领域,在20世纪90年代开始蓬勃发展。机器学习的目标从实现人工智能转变为解决可解决的实践性问题。它将重点从AI中继承的符号方法转向了来自于统计学和概率论的方法和模型<ref name="changing"<ins class="diffchange diffchange-inline">>{{Cite journal | last1 = Langley | first1 = Pat| title = The changing science of machine learning | doi = 10.1007</ins>/<ins class="diffchange diffchange-inline">s10994-011-5242-y | journal = [[Machine Learning (journal)|Machine Learning]]| volume = 82 | issue = 3 | pages = 275–279 | year = 2011 | doi-access = free }}</ref</ins>>,同时也受益于数字化信息日益增长的普及性,以及互联网传播信息的能力。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=28334&oldid=prev
2022年1月7日 (五) 12:13 薄荷
2022-01-07T12:13:07Z
<p></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2022年1月7日 (五) 12:13的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l49" >第49行:</td>
<td colspan="2" class="diff-lineno">第49行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>然而,对逻辑的、基于知识的方法的日益重视,导致人工智能和机器学习之间产生了裂痕,概率系统受到数据采集和数据表示的理论和实践问题的困扰<ref name="aima" />。到1980年,[https://en.wikipedia.org/wiki/Expert_system 专家系统]已经主导了人工智能,而统计方法不再受欢迎<ref name="changing"<del class="diffchange diffchange-inline">>{{Cite journal | last1 = Langley | first1 = Pat| title = The changing science of machine learning |journal = Machine Learning| volume = 82 | issue = 3 | pages = 275–279 | year = 2011 }}<</del>/<del class="diffchange diffchange-inline">ref</del>>。</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>然而,对逻辑的、基于知识的方法的日益重视,导致人工智能和机器学习之间产生了裂痕,概率系统受到数据采集和数据表示的理论和实践问题的困扰<ref name="aima" />。到1980年,[https://en.wikipedia.org/wiki/Expert_system 专家系统]已经主导了人工智能,而统计方法不再受欢迎<ref name="changing"/>。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>基于符号与知识的学习的工作仍然属于AI领域,这促成了归纳逻辑编程,但更多的在模式识别和信息检索</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>基于符号与知识的学习的工作仍然属于AI领域,这促成了归纳逻辑编程,但更多的在模式识别和信息检索</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><ref name="aima">Russell, Stuart; Norvig, Peter (2003) [1995]. [https://en.wikipedia.org/wiki/Artificial_Intelligence:_A_Modern_Approach ''Artificial Intelligence: A Modern Approach''] (2nd ed.). Prentice Hall. ISBN 978-0137903955.</ref>方面的统计方法的研究已经超出了人工智能本身的范围。神经网络的研究几乎同时被人工智能和计算机科学所抛弃。而在AI/CS领域之外,这条路线也被其他学科的研究人员奉为“连接主义”而继续存在,包括Hopfield、Rumelhart和Hinton。他们的主要成功是在上世纪80年代中期重新发明了[[反向传播算法]]</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><ref name="aima">Russell, Stuart; Norvig, Peter (2003) [1995]. [https://en.wikipedia.org/wiki/Artificial_Intelligence:_A_Modern_Approach ''Artificial Intelligence: A Modern Approach''] (2nd ed.). Prentice Hall. ISBN 978-0137903955.</ref>方面的统计方法的研究已经超出了人工智能本身的范围。神经网络的研究几乎同时被人工智能和计算机科学所抛弃。而在AI/CS领域之外,这条路线也被其他学科的研究人员奉为“连接主义”而继续存在,包括Hopfield、Rumelhart和Hinton。他们的主要成功是在上世纪80年代中期重新发明了[[反向传播算法]]</div></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l80" >第80行:</td>
<td colspan="2" class="diff-lineno">第80行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>然而,日益强调的'''基于知识的逻辑方法 Knowledge-based Approach'''导致了人工智能和机器学习之间的裂痕。概率系统一直被数据获取和表示的理论和实际问题所困扰。<ref name="changing"<del class="diffchange diffchange-inline">>{{Cite journal | last1 = Langley | first1 = Pat| title = The changing science of machine learning | doi = 10.1007</del>/<del class="diffchange diffchange-inline">s10994-011-5242-y | journal = Machine Learning (journal)| volume = 82 | issue = 3 | pages = 275–279 | year = 2011 | pmid = | pmc = | doi-access = free }}</ref</del>>在人工智能内部,符号/知识学习的工作确实在继续,导致了归纳逻辑编程,但更多的统计研究现在已经超出了人工智能本身的领域,即模式识别和信息检索。<ref name="aima" />神经网络的研究几乎在同一时间被人工智能和计算机科学领域所抛弃,但这种思路却在人工智能/计算机之外的领域被延续了下来,被其他学科的研究人员称为“连接主义”。(编者注:连接主义又称为仿生学派或生理学派,其主要原理为神经网络及神经网络间的连接机制与学习算法。)包括Hopfield、Rumelhart和Hinton。他们的主要成就集中在20世纪80年代中期,在这一阶段神经网络的方法随着反向传播算法的出现而重新被世人所重视。<ref name="aima" /></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>然而,日益强调的'''基于知识的逻辑方法 Knowledge-based Approach'''导致了人工智能和机器学习之间的裂痕。概率系统一直被数据获取和表示的理论和实际问题所困扰。<ref name="changing"/>在人工智能内部,符号/知识学习的工作确实在继续,导致了归纳逻辑编程,但更多的统计研究现在已经超出了人工智能本身的领域,即模式识别和信息检索。<ref name="aima" />神经网络的研究几乎在同一时间被人工智能和计算机科学领域所抛弃,但这种思路却在人工智能/计算机之外的领域被延续了下来,被其他学科的研究人员称为“连接主义”。(编者注:连接主义又称为仿生学派或生理学派,其主要原理为神经网络及神经网络间的连接机制与学习算法。)包括Hopfield、Rumelhart和Hinton。他们的主要成就集中在20世纪80年代中期,在这一阶段神经网络的方法随着反向传播算法的出现而重新被世人所重视。<ref name="aima" /></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l244" >第244行:</td>
<td colspan="2" class="diff-lineno">第244行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>它在生物信息学和'''自然语言处理 Natural Language Processing'''中特别有用。戈登·普洛特金 Gordon Plotkin和埃胡德·夏皮罗 Ehud Shapiro为归纳机器学习在逻辑上奠定了最初的理论基础。<ref>Plotkin G.D. [https://www.era.lib.ed.ac.uk/bitstream/handle/1842/6656/Plotkin1972.pdf;sequence=1 Automatic Methods of Inductive Inference], PhD thesis, University of Edinburgh, 1970.</ref><ref>Shapiro, Ehud Y. [http://ftp.cs.yale.edu/publications/techreports/tr192.pdf Inductive inference of theories from facts], Research Report 192, Yale University, Department of Computer Science, 1981. Reprinted in J.-L. Lassez, G. Plotkin (Eds.), Computational Logic, The MIT Press, Cambridge, MA, 1991, pp. 199–254.</ref><ref>Shapiro, Ehud Y. (1983). ''Algorithmic program debugging''. Cambridge, Mass: MIT Press. <del class="diffchange diffchange-inline">{{ISBN|0-262-19218-7}}</del></ref>Shapiro在1981年实现了他们的第一个模型推理系统: 一个从正反例中归纳推断逻辑程序的 Prolog 程序。<ref>Shapiro, Ehud Y. "[http://dl.acm.org/citation.cfm?id=1623364 The model inference system]." Proceedings of the 7th international joint conference on Artificial intelligence-Volume 2. Morgan Kaufmann Publishers Inc., 1981.</ref>这里的”归纳“指的是哲学上的归纳,通过提出一个理论来解释观察到的事实,而不是数学归纳法证明了一个有序集合的所有成员的性质。</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>它在生物信息学和'''自然语言处理 Natural Language Processing'''中特别有用。戈登·普洛特金 Gordon Plotkin和埃胡德·夏皮罗 Ehud Shapiro为归纳机器学习在逻辑上奠定了最初的理论基础。<ref>Plotkin G.D. [https://www.era.lib.ed.ac.uk/bitstream/handle/1842/6656/Plotkin1972.pdf;sequence=1 Automatic Methods of Inductive Inference], PhD thesis, University of Edinburgh, 1970.</ref><ref>Shapiro, Ehud Y. [http://ftp.cs.yale.edu/publications/techreports/tr192.pdf Inductive inference of theories from facts], Research Report 192, Yale University, Department of Computer Science, 1981. Reprinted in J.-L. Lassez, G. Plotkin (Eds.), Computational Logic, The MIT Press, Cambridge, MA, 1991, pp. 199–254.</ref><ref>Shapiro, Ehud Y. (1983). ''Algorithmic program debugging''. Cambridge, Mass: MIT Press.</ref>Shapiro在1981年实现了他们的第一个模型推理系统: 一个从正反例中归纳推断逻辑程序的 Prolog 程序。<ref>Shapiro, Ehud Y. "[http://dl.acm.org/citation.cfm?id=1623364 The model inference system]." Proceedings of the 7th international joint conference on Artificial intelligence-Volume 2. Morgan Kaufmann Publishers Inc., 1981.</ref>这里的”归纳“指的是哲学上的归纳,通过提出一个理论来解释观察到的事实,而不是数学归纳法证明了一个有序集合的所有成员的性质。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=25492&oldid=prev
薄荷:/* 局限 */
2021-08-04T13:45:14Z
<p><span dir="auto"><span class="autocomment">局限</span></span></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2021年8月4日 (三) 13:45的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l378" >第378行:</td>
<td colspan="2" class="diff-lineno">第378行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==局限==</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==局限==</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>虽然机器学习在某些领域是革命性的,但有效的机器学习仍是困难的,因为找出模式很难,而且往往没有足够的训练数据;因此,许多机器学习程序往往无法达到预期值</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>虽然机器学习在某些领域是革命性的,但有效的机器学习仍是困难的,因为找出模式很难,而且往往没有足够的训练数据;因此,许多机器学习程序往往无法达到预期值</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><ref></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ref>[http://web.archive.org/web/20170320225010/https://www.bloomberg.com/news/articles/2016-11-10/why-machine-learning-models-often-fail-to-learn-quicktake-q-a "Why Machine Learning Models Often Fail to Learn: QuickTake Q&A"]. ''Bloomberg.com.'' 2016-11-10. Retrieved 2017-04-10.</ref><ref>[https://hbr.org/2017/04/the-first-wave-of-corporate-ai-is-doomed-to-fail "The First Wave of Corporate AI Is Doomed to Fail"]. Harvard Business Review. 2017-04-18. Retrieved 2018-08-20.</ref><ref>[https://venturebeat.com/2016/09/17/why-the-a-i-euphoria-is-doomed-to-fail/ "Why the A.I. euphoria is doomed to fail"]. VentureBeat. 2016-09-18. Retrieved 2018-08-20.</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[http://web.archive.org/web/20170320225010/https://www.bloomberg.com/news/articles/2016-11-10/why-machine-learning-models-often-fail-to-learn-quicktake-q-a "Why Machine Learning Models Often Fail to Learn: QuickTake Q&A"]. ''Bloomberg.com.'' 2016-11-10. Retrieved 2017-04-10.</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div></ref> <ins class="diffchange diffchange-inline">。造成这种情况的原因很多:缺乏(适当的)数据、无法访问数据、数据偏见、隐私问题、错误的任务选择和算法、错误的工具和人员、缺乏资源和评估问题</ins><ref></div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div></ref></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[https://www.kdnuggets.com/2018/07/why-machine-learning-project-fail.html|title=9 Reasons why your machine learning project will fail "9 Reasons why your machine learning project will fail"]. www.kdnuggets.com. Retrieved 2018-08-20.</ref>。</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><ref></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div> </div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[https://hbr.org/2017/04/the-first-wave-of-corporate-ai-is-doomed-to-fail "The First Wave of Corporate AI Is Doomed to Fail"]. Harvard Business Review. 2017-04-18. Retrieved 2018-08-20.</div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div></ref></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><ref></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[https://venturebeat.com/2016/09/17/why-the-a-i-euphoria-is-doomed-to-fail/ "Why the A.I. euphoria is doomed to fail"]. VentureBeat. 2016-09-18. Retrieved 2018-08-20.</div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div></ref> <del class="diffchange diffchange-inline">。</del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del class="diffchange diffchange-inline">造成这种情况的原因很多:缺乏(适当的)数据、无法访问数据、数据偏见、隐私问题、错误的任务选择和算法、错误的工具和人员、缺乏资源和评估问题</del><ref></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[https://www.kdnuggets.com/2018/07/why-machine-learning-project-fail.html|title=9 Reasons why your machine learning project will fail "9 Reasons why your machine learning project will fail"]. www.kdnuggets.com. Retrieved 2018-08-20.</div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div></ref>。</div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>机器学习方法尤其会受到不同数据偏见的影响。只针对当前客户进行训练的机器学习系统可能无法预测训练数据中未表示的新客户组的需求。当接受人工数据训练时,机器学习很可能会产生与社会上已经存在的相同的成体制偏见和无意识偏见<ref>{{Cite journal|last=Garcia|first=Megan|date=2016|title=Racist in the Machine|url=https://read.dukeupress.edu/world-policy-journal/article/33/4/111-117/30942|journal=World Policy Journal|language=en|volume=33|issue=4|pages=111–117|issn:0740-2775}}</ref> 。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>机器学习方法尤其会受到不同数据偏见的影响。只针对当前客户进行训练的机器学习系统可能无法预测训练数据中未表示的新客户组的需求。当接受人工数据训练时,机器学习很可能会产生与社会上已经存在的相同的成体制偏见和无意识偏见<ref>{{Cite journal|last=Garcia|first=Megan|date=2016|title=Racist in the Machine|url=https://read.dukeupress.edu/world-policy-journal/article/33/4/111-117/30942|journal=World Policy Journal|language=en|volume=33|issue=4|pages=111–117|issn:0740-2775}}</ref> 。</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>从数据中学到的语言模型已被证明含有类似人类的偏见<ref>{{Cite journal|last=Caliskan|first=Aylin|last2=Bryson|first2=Joanna J.|last3=Narayanan|first3=Arvind|date=2017-04-14|title=Semantics derived automatically from language corpora contain human-like biases|url=http://science.sciencemag.org/content/356/6334/183|journal=Science|language=en|volume=356|issue=6334|pages=183–186<del class="diffchange diffchange-inline">|doi:10.1126/science.aal4230|issn:0036-8075|pmid:28408601</del>}}</ref><ref>Wang, Xinan; Dasgupta, Sanjoy (2016), Lee, D. D.; Sugiyama, M.; Luxburg, U. V.; Guyon, I., eds., [http://papers.nips.cc/paper/6227-an-algorithm-for-l1-nearest-neighbor-search-via-monotonic-embedding.pdf "An algorithm for L1 nearest neighbor search via monotonic embedding"] (PDF), ''Advances in Neural Information Processing Systems 29'', Curran Associates, Inc., pp. 983–991, Retrieved 2018-08-20</ref> 。用于犯罪风险评估的机器学习系统被发现对黑人有偏见<ref>[https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing "Machine Bias"]. ProPublica. Julia Angwin, Jeff Larson, Lauren Kirchner, Surya Mattu. 2016-05-23. Retrieved 2018-08-20.</ref><ref>[https://www.nytimes.com/2017/10/26/opinion/algorithm-compas-sentencing-bias.html "Opinion | When an Algorithm Helps Send You to Prison"]. New York Times. Retrieved 2018-08-20.</ref> 。在2015年,谷歌上黑人的照片常常被贴上大猩猩的标签<ref>[https://www.bbc.co.uk/news/technology-33347866 "Google apologises for racist blunder"]. BBC News. 2015-07-01. Retrieved 2018-08-20.</ref> ,而到2018年,这仍然没有得到很好的解决,但据报道,谷歌仍在使用变通方法将所有大猩猩从训练数据中删除,因此根本无法识别真正的大猩猩<ref>[https://www.theverge.com/2018/1/12/16882408/google-racist-gorillas-photo-recognition-algorithm-ai "Google 'fixed' its racist algorithm by removing gorillas from its image-labeling tech"]. The Verge. Retrieved 2018-08-20.</ref>。在许多其他系统中<ref>[https://www.nytimes.com/2016/06/26/opinion/sunday/artificial-intelligences-white-guy-problem.html "Opinion | Artificial Intelligence's White Guy Problem"]. New York Times. Retrieved 2018-08-20.</ref> ,也发现了识别非白人的类似问题。2016年,微软测试了一个从Twitter上学习的[https://en.wikipedia.org/wiki/Chatbot 聊天机器人],而后者却很快学会了种族主义和性别歧视的语言<ref>Metz, Rachel. [https://www.technologyreview.com/s/601111/why-microsoft-accidentally-unleashed-a-neo-nazi-sexbot/ "Why Microsoft's teen chatbot, Tay, said lots of awful things online"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。由于这些挑战,机器在其他领域的有效使用仍有很长的路要走<ref>Simonite, Tom. [https://www.technologyreview.com/s/603944/microsoft-ai-isnt-yet-adaptable-enough-to-help-businesses/ "Microsoft says its racist chatbot illustrates how AI isn't adaptable enough to help most businesses"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。2018年,[https://en.wikipedia.org/wiki/Uber Uber]的一辆自动驾驶汽车未能检测到行人并导致其在事故中丧生。<ref>[https://www.economist.com/the-economist-explains/2018/05/29/why-ubers-self-driving-car-killed-a-pedestrian "Why Uber's self-driving car killed a pedestrian"]. The Economist. Retrieved 2018-08-20.</ref>。IBM Watson系统在医疗保健领域使用机器学习的尝试,即便经过多年的时间和数十亿美元的投资,也未能实现<ref></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>从数据中学到的语言模型已被证明含有类似人类的偏见<ref>{{Cite journal|last=Caliskan|first=Aylin|last2=Bryson|first2=Joanna J.|last3=Narayanan|first3=Arvind|date=2017-04-14|title=Semantics derived automatically from language corpora contain human-like biases|url=http://science.sciencemag.org/content/356/6334/183|journal=Science|language=en|volume=356|issue=6334|pages=183–186}}</ref><ref>Wang, Xinan; Dasgupta, Sanjoy (2016), Lee, D. D.; Sugiyama, M.; Luxburg, U. V.; Guyon, I., eds., [http://papers.nips.cc/paper/6227-an-algorithm-for-l1-nearest-neighbor-search-via-monotonic-embedding.pdf "An algorithm for L1 nearest neighbor search via monotonic embedding"] (PDF), ''Advances in Neural Information Processing Systems 29'', Curran Associates, Inc., pp. 983–991, Retrieved 2018-08-20</ref> 。用于犯罪风险评估的机器学习系统被发现对黑人有偏见<ref>[https://www.propublica.org/article/machine-bias-risk-assessments-in-criminal-sentencing "Machine Bias"]. ProPublica. Julia Angwin, Jeff Larson, Lauren Kirchner, Surya Mattu. 2016-05-23. Retrieved 2018-08-20.</ref><ref>[https://www.nytimes.com/2017/10/26/opinion/algorithm-compas-sentencing-bias.html "Opinion | When an Algorithm Helps Send You to Prison"]. New York Times. Retrieved 2018-08-20.</ref> 。在2015年,谷歌上黑人的照片常常被贴上大猩猩的标签<ref>[https://www.bbc.co.uk/news/technology-33347866 "Google apologises for racist blunder"]. BBC News. 2015-07-01. Retrieved 2018-08-20.</ref> ,而到2018年,这仍然没有得到很好的解决,但据报道,谷歌仍在使用变通方法将所有大猩猩从训练数据中删除,因此根本无法识别真正的大猩猩<ref>[https://www.theverge.com/2018/1/12/16882408/google-racist-gorillas-photo-recognition-algorithm-ai "Google 'fixed' its racist algorithm by removing gorillas from its image-labeling tech"]. The Verge. Retrieved 2018-08-20.</ref>。在许多其他系统中<ref>[https://www.nytimes.com/2016/06/26/opinion/sunday/artificial-intelligences-white-guy-problem.html "Opinion | Artificial Intelligence's White Guy Problem"]. New York Times. Retrieved 2018-08-20.</ref> ,也发现了识别非白人的类似问题。2016年,微软测试了一个从Twitter上学习的[https://en.wikipedia.org/wiki/Chatbot 聊天机器人],而后者却很快学会了种族主义和性别歧视的语言<ref>Metz, Rachel. [https://www.technologyreview.com/s/601111/why-microsoft-accidentally-unleashed-a-neo-nazi-sexbot/ "Why Microsoft's teen chatbot, Tay, said lots of awful things online"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。由于这些挑战,机器在其他领域的有效使用仍有很长的路要走<ref>Simonite, Tom. [https://www.technologyreview.com/s/603944/microsoft-ai-isnt-yet-adaptable-enough-to-help-businesses/ "Microsoft says its racist chatbot illustrates how AI isn't adaptable enough to help most businesses"]. MIT Technology Review. Retrieved 2018-08-20.</ref>。2018年,[https://en.wikipedia.org/wiki/Uber Uber]的一辆自动驾驶汽车未能检测到行人并导致其在事故中丧生。<ref>[https://www.economist.com/the-economist-explains/2018/05/29/why-ubers-self-driving-car-killed-a-pedestrian "Why Uber's self-driving car killed a pedestrian"]. The Economist. Retrieved 2018-08-20.</ref>。IBM Watson系统在医疗保健领域使用机器学习的尝试,即便经过多年的时间和数十亿美元的投资,也未能实现<ref></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[https://www.statnews.com/2018/07/25/ibm-watson-recommended-unsafe-incorrect-treatments/ "IBM's Watson recommended 'unsafe and incorrect' cancer treatments - STAT"]. STAT. 2018-07-25. Retrieved 2018-08-21.</ref><ref>Hernandez, Daniela; Greenwald, Ted (2018-08-11). [https://www.wsj.com/articles/ibm-bet-billions-that-watson-could-improve-cancer-treatment-it-hasnt-worked-1533961147 "IBM Has a Watson Dilemma"].Wall Street Journal. ISSN 0099-9660. Retrieved 2018-08-21.</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>[https://www.statnews.com/2018/07/25/ibm-watson-recommended-unsafe-incorrect-treatments/ "IBM's Watson recommended 'unsafe and incorrect' cancer treatments - STAT"]. STAT. 2018-07-25. Retrieved 2018-08-21.</ref><ref>Hernandez, Daniela; Greenwald, Ted (2018-08-11). [https://www.wsj.com/articles/ibm-bet-billions-that-watson-could-improve-cancer-treatment-it-hasnt-worked-1533961147 "IBM Has a Watson Dilemma"].Wall Street Journal. ISSN 0099-9660. Retrieved 2018-08-21.</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div></ref>。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div></ref>。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"><br></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==模型评估==</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==模型评估==</div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=25487&oldid=prev
薄荷:/* 基于规则的机器学习算法 */
2021-08-04T13:32:10Z
<p><span dir="auto"><span class="autocomment">基于规则的机器学习算法</span></span></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2021年8月4日 (三) 13:32的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l220" >第220行:</td>
<td colspan="2" class="diff-lineno">第220行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 基于规则的机器学习算法 ====</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 基于规则的机器学习算法 ====</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[https://en.wikipedia.org/wiki/Rule-based_machine_learning 基于规则的机器学习]是任何机器学习方法的通用术语,它通过识别、学习或演化“规则”来存储、操作或应用知识。基于规则的机器学习者的定义特征是识别和使用一组关系规则,这些规则共同表示系统获取的知识。这与其他机器学习者不同,这些机器学习者通常会识别出一个可以普遍应用于任何实例的奇异模型,以便进行预测<ref>{{Cite journal|last=Bassel|first=George W.|last2=Glaab|first2=Enrico|last3=Marquez|first3=Julietta|last4=Holdsworth|first4=Michael J.|last5=Bacardit|first5=Jaume|date=2011-09-01|title=Functional Network Construction in Arabidopsis Using Rule-Based Machine Learning on Large-Scale Data Sets|url=http://www.plantcell.org/content/23/9/3101|journal=The Plant Cell|language=en|volume=23|issue=9|pages=3101–3116<del class="diffchange diffchange-inline">|doi:10.1105/tpc.111.088153|issn:1532-298X|pmc:3203449|pmid:21896882</del>}}</ref> 。基于规则的机器学习方法包括[https://en.wikipedia.org/wiki/Learning_classifier_system 学习分类器系统]、[https://en.wikipedia.org/wiki/Association_rule_learning 关联规则学习]和[https://en.wikipedia.org/wiki/Artificial_immune_system 人工免疫系统]。</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[https://en.wikipedia.org/wiki/Rule-based_machine_learning 基于规则的机器学习]是任何机器学习方法的通用术语,它通过识别、学习或演化“规则”来存储、操作或应用知识。基于规则的机器学习者的定义特征是识别和使用一组关系规则,这些规则共同表示系统获取的知识。这与其他机器学习者不同,这些机器学习者通常会识别出一个可以普遍应用于任何实例的奇异模型,以便进行预测<ref>{{Cite journal|last=Bassel|first=George W.|last2=Glaab|first2=Enrico|last3=Marquez|first3=Julietta|last4=Holdsworth|first4=Michael J.|last5=Bacardit|first5=Jaume|date=2011-09-01|title=Functional Network Construction in Arabidopsis Using Rule-Based Machine Learning on Large-Scale Data Sets|url=http://www.plantcell.org/content/23/9/3101|journal=The Plant Cell|language=en|volume=23|issue=9|pages=3101–3116}}</ref> 。基于规则的机器学习方法包括[https://en.wikipedia.org/wiki/Learning_classifier_system 学习分类器系统]、[https://en.wikipedia.org/wiki/Association_rule_learning 关联规则学习]和[https://en.wikipedia.org/wiki/Artificial_immune_system 人工免疫系统]。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=25486&oldid=prev
薄荷:/* 学习分类器 */
2021-08-04T13:31:35Z
<p><span dir="auto"><span class="autocomment">学习分类器</span></span></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2021年8月4日 (三) 13:31的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l233" >第233行:</td>
<td colspan="2" class="diff-lineno">第233行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=====学习分类器=====</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=====学习分类器=====</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>'''学习分类器系统 Learning Classifier Systems(LCS)'''是一组基于规则的机器学习算法,它将发现组件(通常是[[遗传算法]])与学习组件(执行有[[监督学习]]、[[强化学习]]或[[无监督学习]])结合起来。他们试图找出一套与情境相关的规则,这些规则以一种分段的方式,集体存储和应用知识,以便进行预测<ref>{{Cite journal|last=Urbanowicz|first=Ryan J.|last2=Moore|first2=Jason H.|date=2009-09-22|title=Learning Classifier Systems: A Complete Introduction, Review, and Roadmap|url=http://www.hindawi.com/archive/2009/736398/|journal=Journal of Artificial Evolution and Applications|language=en|volume=2009|pages=1–25<del class="diffchange diffchange-inline">|issn:1687-6229</del>}}</ref>。</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>'''学习分类器系统 Learning Classifier Systems(LCS)'''是一组基于规则的机器学习算法,它将发现组件(通常是[[遗传算法]])与学习组件(执行有[[监督学习]]、[[强化学习]]或[[无监督学习]])结合起来。他们试图找出一套与情境相关的规则,这些规则以一种分段的方式,集体存储和应用知识,以便进行预测<ref>{{Cite journal|last=Urbanowicz|first=Ryan J.|last2=Moore|first2=Jason H.|date=2009-09-22|title=Learning Classifier Systems: A Complete Introduction, Review, and Roadmap|url=http://www.hindawi.com/archive/2009/736398/|journal=Journal of Artificial Evolution and Applications|language=en|volume=2009|pages=1–25}}</ref>。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=25485&oldid=prev
薄荷:/* 模型评估 */
2021-08-04T13:31:00Z
<p><span dir="auto"><span class="autocomment">模型评估</span></span></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2021年8月4日 (三) 13:31的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l401" >第401行:</td>
<td colspan="2" class="diff-lineno">第401行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>除了总体准确性外,调查人员还经常报告敏感性和特异性,即真阳性率(TPR)和真阴性率(TNR)。同样,调查人员有时报告[https://en.wikipedia.org/wiki/False_positive_rate 假阳性率](FPR)和[https://en.wikipedia.org/wiki/False_positives_and_false_negatives#False_positive_and_false_negative_rates 假阴性率](FNR)。然而,这些比率不能显示它们的分子和分母。[https://en.wikipedia.org/wiki/Total_operating_characteristic 总运行特性](TOC)是表示模型诊断能力的一种有效方法。TOC显示上述比率的分子和分母,因此TOC提供的信息比常用的[https://en.wikipedia.org/wiki/Receiver_operating_characteristic 受试者工作特征](ROC)和曲线下ROC的关联区域(AUC)提供的信息更多<ref>{{cite journal|last1=Pontius|first1=Robert Gilmore|last2=Si|first2=Kangping|title=The total operating characteristic to measure diagnostic ability for multiple thresholds| journal=International Journal of Geographical Information Science|volume=28|issue=3|year=2014|pages=570–583<del class="diffchange diffchange-inline">|doi:10.1080/13658816.2013.862623</del>}}</ref>。</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>除了总体准确性外,调查人员还经常报告敏感性和特异性,即真阳性率(TPR)和真阴性率(TNR)。同样,调查人员有时报告[https://en.wikipedia.org/wiki/False_positive_rate 假阳性率](FPR)和[https://en.wikipedia.org/wiki/False_positives_and_false_negatives#False_positive_and_false_negative_rates 假阴性率](FNR)。然而,这些比率不能显示它们的分子和分母。[https://en.wikipedia.org/wiki/Total_operating_characteristic 总运行特性](TOC)是表示模型诊断能力的一种有效方法。TOC显示上述比率的分子和分母,因此TOC提供的信息比常用的[https://en.wikipedia.org/wiki/Receiver_operating_characteristic 受试者工作特征](ROC)和曲线下ROC的关联区域(AUC)提供的信息更多<ref>{{cite journal|last1=Pontius|first1=Robert Gilmore|last2=Si|first2=Kangping|title=The total operating characteristic to measure diagnostic ability for multiple thresholds| journal=International Journal of Geographical Information Science|volume=28|issue=3|year=2014|pages=570–583}}</ref>。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2"> </td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;"><br></ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==规范准则==</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==规范准则==</div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=25484&oldid=prev
2021年8月4日 (三) 13:21 薄荷
2021-08-04T13:21:14Z
<p></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2021年8月4日 (三) 13:21的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l28" >第28行:</td>
<td colspan="2" class="diff-lineno">第28行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>===机器学习的任务===</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>===机器学习的任务===</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>机器学习任务通常分为两大类,取决于学习系统是否存在学习“信号”或“反馈”:</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>机器学习任务通常分为两大类,取决于学习系统是否存在学习“信号”或“反馈”:</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>* '''监督学习'''<del class="diffchange diffchange-inline">:向计算机展示由“教师”提供的示例输入及其期望的输出,目标是学习将输入[https://en.wikipedia.org/wiki/Map_(mathematics) 映射]到输出的一般规则。作为特例,输入信号只能被部分提供,或仅限于特定反馈:</del></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>* '''监督学习'''<ins class="diffchange diffchange-inline">:向计算机展示由“教师”提供的示例输入及其期望的输出,目标是学习将输入映射到输出的一般规则。作为特例,输入信号只能被部分提供,或仅限于特定反馈:</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** '''半监督学习''':只提供给计算机一个不完整的训练信号:一个训练集,其中有一些(通常很多)的目标输出丢失。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** '''半监督学习''':只提供给计算机一个不完整的训练信号:一个训练集,其中有一些(通常很多)的目标输出丢失。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** '''主动学习''':计算机只能获得有限的实例集(基于预算)的训练标签,还必须优化对象的选择以获取标签。当交互使用时,可以向用户展示这些对象以供标签。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>** '''主动学习''':计算机只能获得有限的实例集(基于预算)的训练标签,还必须优化对象的选择以获取标签。当交互使用时,可以向用户展示这些对象以供标签。</div></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l77" >第77行:</td>
<td colspan="2" class="diff-lineno">第77行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== 与人工智能的关系 ===</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>=== 与人工智能的关系 ===</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>作为一项科研成果,机器学习源于对人工智能的探索。在人工智能这一学科研究的早期,一些研究人员对于让机器从数据中进行学习这一问题很感兴趣。他们试图用各种符号方法甚至是当时被称为'''”神经网络 Neural Networks”'''<del class="diffchange diffchange-inline">的方法来处理这个问题;但这些方法大部分是感知器或其他模型。后来这些模型随着统计学中广义线性模型的发展而重新出现在大众视野中,与此同时概率推理的方法也被广泛使用,特别是在自动医疗诊断问题上。</del><ref>Russell, Stuart; Norvig, Peter (2003) [1995]. Artificial Intelligence: A Modern Approach (2nd ed.). Prentice Hall. ISBN 978-0137903955.</ref></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>作为一项科研成果,机器学习源于对人工智能的探索。在人工智能这一学科研究的早期,一些研究人员对于让机器从数据中进行学习这一问题很感兴趣。他们试图用各种符号方法甚至是当时被称为'''”神经网络 Neural Networks”'''<ins class="diffchange diffchange-inline">的方法来处理这个问题;但这些方法大部分是感知器或其他模型。后来这些模型随着统计学中广义线性模型的发展而重新出现在大众视野中,与此同时概率推理的方法也被广泛使用,特别是在自动医疗诊断问题上。</ins><ref>Russell, Stuart; Norvig, Peter (2003) [1995]. Artificial Intelligence: A Modern Approach (2nd ed.). Prentice Hall. ISBN 978-0137903955.</ref></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l141" >第141行:</td>
<td colspan="2" class="diff-lineno">第141行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>在'''弱监督学习 Weak Supervision'''<del class="diffchange diffchange-inline">中,训练标签是有噪声的、有限的或不精确的; 然而,这些标签使用起来往往更加“实惠”——这种数据更容易得到、更容易拥有更大的有效训练集。</del><ref>{{Cite web|url=https://hazyresearch.github.io/snorkel/blog/ws_blog_post.html|title=Weak Supervision: The New Programming Paradigm for Machine Learning|author1=Alex Ratner |author2=Stephen Bach |author3=Paroma Varma |author4=Chris |others= referencing work by many other members of Hazy Research|website=hazyresearch.github.io|access-date=2019-06-06}}</ref></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>在'''弱监督学习 Weak Supervision'''<ins class="diffchange diffchange-inline">中,训练标签是有噪声的、有限的或不精确的;然而,这些标签使用起来往往更加“实惠”——这种数据更容易得到、更容易拥有更大的有效训练集。</ins><ref>{{Cite web|url=https://hazyresearch.github.io/snorkel/blog/ws_blog_post.html|title=Weak Supervision: The New Programming Paradigm for Machine Learning|author1=Alex Ratner |author2=Stephen Bach |author3=Paroma Varma |author4=Chris |others= referencing work by many other members of Hazy Research|website=hazyresearch.github.io|access-date=2019-06-06}}</ref></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l158" >第158行:</td>
<td colspan="2" class="diff-lineno">第158行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>在情境中执行动作 <del class="diffchange diffchange-inline">a;</del></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>在情境中执行动作 <ins class="diffchange diffchange-inline">a;</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>接受结果状态 <del class="diffchange diffchange-inline">s’ ;</del></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>接受结果状态 <ins class="diffchange diffchange-inline">s’;</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>计算处于结果情境 v (s’)<del class="diffchange diffchange-inline">中的情绪;</del></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>计算处于结果情境 v (s’)<ins class="diffchange diffchange-inline">中的情绪;</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l276" >第276行:</td>
<td colspan="2" class="diff-lineno">第276行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 决策树 ====</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 决策树 ====</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>'''决策树 Decision trees'''学习使用[[决策树]]<del class="diffchange diffchange-inline">作为预测模型,它将问题相关的观察结果映射为问题目标值的结论,是统计学、数据挖掘和机器学习中常用的预测建模方法之一。目标变量接受到的一组离散值的树模型称为分类树; 在这些树结构中,叶子代表类标签,分支代表连接到这些类标签的特征。其中目标变量可以取连续值(通常是实数)的决策树称为回归树。在决策分析中,可以使用决策树直观地表示决策和决策。在数据挖掘中,决策树是用来描述数据的,但得到的分类树可以作为决策的输入。</del></div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>'''决策树 Decision trees'''学习使用[[决策树]]<ins class="diffchange diffchange-inline">作为预测模型,它将问题相关的观察结果映射为问题目标值的结论,是统计学、数据挖掘和机器学习中常用的预测建模方法之一。目标变量接受到的一组离散值的树模型称为分类树;在这些树结构中,叶子代表类标签,分支代表连接到这些类标签的特征。其中目标变量可以取连续值(通常是实数)的决策树称为回归树。在决策分析中,可以使用决策树直观地表示决策和决策。在数据挖掘中,决策树是用来描述数据的,但得到的分类树可以作为决策的输入。</ins></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l292" >第292行:</td>
<td colspan="2" class="diff-lineno">第292行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 贝叶斯网络 ====</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 贝叶斯网络 ====</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[[Image:SimpleBayesNetNodes.svg.png|thumb|right|<del class="diffchange diffchange-inline">A simple Bayesian network. Rain influences whether the sprinkler is activated, and both rain and the sprinkler influence whether the grass is wet. </del>一个简单的贝叶斯网路。雨水会影响喷头是否被激活,而雨水和喷头都会影响草地是否湿润。]]</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[[Image:SimpleBayesNetNodes.svg.png|thumb|right|一个简单的贝叶斯网路。雨水会影响喷头是否被激活,而雨水和喷头都会影响草地是否湿润。]]</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''贝叶斯网路 Bayesian Network''',或称信任网络或者有向无环图形模型是通过[[有向无环图]]表示一组随机变量及其条件独立性的概率图形模型。例如,贝叶斯网络可以表示疾病和症状之间的概率关系。给定症状,网络可以用来计算各种疾病出现的概率。有效的算法可以进行推理和学习。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''贝叶斯网路 Bayesian Network''',或称信任网络或者有向无环图形模型是通过[[有向无环图]]表示一组随机变量及其条件独立性的概率图形模型。例如,贝叶斯网络可以表示疾病和症状之间的概率关系。给定症状,网络可以用来计算各种疾病出现的概率。有效的算法可以进行推理和学习。</div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=25483&oldid=prev
薄荷:/* 方法 */
2021-08-04T13:12:54Z
<p><span dir="auto"><span class="autocomment">方法</span></span></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2021年8月4日 (三) 13:12的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l128" >第128行:</td>
<td colspan="2" class="diff-lineno">第128行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''相似性学习 Similarity Learning'''是监督学习领域中与回归和分类密切相关的一个领域,但其目标是从实例中学习如何通过使用相似性函数来衡量两个对象之间的相似程度。它在排名、推荐系统、视觉身份跟踪、人脸验证和'''语者验证 Speaker Verification'''等方面都有应用。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''相似性学习 Similarity Learning'''是监督学习领域中与回归和分类密切相关的一个领域,但其目标是从实例中学习如何通过使用相似性函数来衡量两个对象之间的相似程度。它在排名、推荐系统、视觉身份跟踪、人脸验证和'''语者验证 Speaker Verification'''等方面都有应用。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div><del style="font-weight: bold; text-decoration: none;"></ref></del></div></td><td colspan="2"> </td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 无监督学习 ====</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 无监督学习 ====</div></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l284" >第284行:</td>
<td colspan="2" class="diff-lineno">第283行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''支持向量机 SupportVectorMachine(SVMs)'''是一种用于分类和回归的[[监督学习]]算法。给出一组训练实例,每个样本会被标记为属于两类中的一个,SVM算法建立了一个模型来预测一个新的例子是否属于一个类别或另一个类别。<ref name="CorinnaCortes">{{Cite journal |last1=Cortes |first1=Corinna |authorlink1=Corinna Cortes |last2=Vapnik |first2=Vladimir N. |year=1995 |title=Support-vector networks |journal=[[Machine Learning (journal)|Machine Learning]] |volume=20 |issue=3 |pages=273–297 |doi=10.1007/BF00994018 |doi-access=free }}</ref>支持向量机的训练算法用到的是一种非概率的二进制线性分类器,尽管在概率分类环境中也存在使用支持向量机的方法,如 Platt 缩放法。除了执行线性分类,支持向量机可以有效地执行非线性分类使用所谓的'''核技巧 Kernel trick''',隐式地将模型输入映射到高维特征空间。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''支持向量机 SupportVectorMachine(SVMs)'''是一种用于分类和回归的[[监督学习]]算法。给出一组训练实例,每个样本会被标记为属于两类中的一个,SVM算法建立了一个模型来预测一个新的例子是否属于一个类别或另一个类别。<ref name="CorinnaCortes">{{Cite journal |last1=Cortes |first1=Corinna |authorlink1=Corinna Cortes |last2=Vapnik |first2=Vladimir N. |year=1995 |title=Support-vector networks |journal=[[Machine Learning (journal)|Machine Learning]] |volume=20 |issue=3 |pages=273–297 |doi=10.1007/BF00994018 |doi-access=free }}</ref>支持向量机的训练算法用到的是一种非概率的二进制线性分类器,尽管在概率分类环境中也存在使用支持向量机的方法,如 Platt 缩放法。除了执行线性分类,支持向量机可以有效地执行非线性分类使用所谓的'''核技巧 Kernel trick''',隐式地将模型输入映射到高维特征空间。</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[[Image:<del class="diffchange diffchange-inline">Linear regression</del>.svg|thumb|upright=1.3|Illustration of linear regression on a data set.数据集上的线性回归]]</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[[Image:<ins class="diffchange diffchange-inline">Linear_regression</ins>.svg<ins class="diffchange diffchange-inline">.png</ins>|thumb|upright=1.3|Illustration of linear regression on a data set.数据集上的线性回归]]</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div><br></div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l293" >第293行:</td>
<td colspan="2" class="diff-lineno">第292行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 贝叶斯网络 ====</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 贝叶斯网络 ====</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[[Image:SimpleBayesNetNodes.svg|thumb|right|A simple Bayesian network. Rain influences whether the sprinkler is activated, and both rain and the sprinkler influence whether the grass is wet. 一个简单的贝叶斯网路。雨水会影响喷头是否被激活,而雨水和喷头都会影响草地是否湿润。]]</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[[Image:SimpleBayesNetNodes.svg<ins class="diffchange diffchange-inline">.png</ins>|thumb|right|A simple Bayesian network. Rain influences whether the sprinkler is activated, and both rain and the sprinkler influence whether the grass is wet. 一个简单的贝叶斯网路。雨水会影响喷头是否被激活,而雨水和喷头都会影响草地是否湿润。]]</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''贝叶斯网路 Bayesian Network''',或称信任网络或者有向无环图形模型是通过[[有向无环图]]表示一组随机变量及其条件独立性的概率图形模型。例如,贝叶斯网络可以表示疾病和症状之间的概率关系。给定症状,网络可以用来计算各种疾病出现的概率。有效的算法可以进行推理和学习。</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>'''贝叶斯网路 Bayesian Network''',或称信任网络或者有向无环图形模型是通过[[有向无环图]]表示一组随机变量及其条件独立性的概率图形模型。例如,贝叶斯网络可以表示疾病和症状之间的概率关系。给定症状,网络可以用来计算各种疾病出现的概率。有效的算法可以进行推理和学习。</div></td></tr>
</table>
薄荷
https://wiki.swarma.org/index.php?title=%E6%9C%BA%E5%99%A8%E5%AD%A6%E4%B9%A0_Machine_Learning&diff=25482&oldid=prev
薄荷:/* 人工神经网络 */
2021-08-04T12:55:15Z
<p><span dir="auto"><span class="autocomment">人工神经网络</span></span></p>
<table class="diff diff-contentalign-left diff-editfont-monospace" data-mw="interface">
<col class="diff-marker" />
<col class="diff-content" />
<col class="diff-marker" />
<col class="diff-content" />
<tr class="diff-title" lang="zh-Hans-CN">
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">←上一版本</td>
<td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">2021年8月4日 (三) 12:55的版本</td>
</tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l259" >第259行:</td>
<td colspan="2" class="diff-lineno">第259行:</td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 人工神经网络====</div></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>==== 人工神经网络====</div></td></tr>
<tr><td class='diff-marker'>−</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[[File:<del class="diffchange diffchange-inline">Colored neural network</del>.svg|thumb|300px|<del class="diffchange diffchange-inline">An artificial neural network is an interconnected group of nodes, akin to the vast network of [[neuron]]s in a [[brain]]. Here, each circular node represents an [[artificial neuron]] and an arrow represents a connection from the output of one artificial neuron to the input of another.'''人工神经网络 Artificial Neural Network,ANN'''是一组相互连接的节点,类似于大脑中庞大的神经元网络。在这里,每个圆形节点代表一个人工</del>'''神经元 Neuron''',一个箭头代表从一个人工神经元的输出到另一个输入的连接]]</div></td><td class='diff-marker'>+</td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[[File:<ins class="diffchange diffchange-inline">Colored_neural_network</ins>.svg<ins class="diffchange diffchange-inline">.png</ins>|thumb|300px|<ins class="diffchange diffchange-inline">人工神经网络是一组相互连接的节点,类似于大脑中庞大的神经元网络。在这里,每个圆形节点代表一个人工</ins>'''神经元 Neuron''',一个箭头代表从一个人工神经元的输出到另一个输入的连接]]</div></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
<tr><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td><td class='diff-marker'> </td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"></td></tr>
</table>
薄荷