7,129
个编辑
更改
跳到导航
跳到搜索
第712行：
第712行： − + − − Usually, machine learning models require a lot of data in order for them to perform well. Usually, when training a machine learning model, one needs to collect a large, representative sample of data from a training set. Data from the training set can be as varied as a corpus of text, a collection of images, and data collected from individual users of a service. [[Overfitting]] is something to watch out for when training a machine learning model. − − Usually, machine learning models require a lot of data in order for them to perform well. Usually, when training a machine learning model, one needs to collect a large, representative sample of data from a training set. Data from the training set can be as varied as a corpus of text, a collection of images, and data collected from individual users of a service. Overfitting is something to watch out for when training a machine learning model. − − +
→训练模型 Training models
<ref>{{cite journal |last1=Zhang |first1=Jun |last2=Zhan |first2=Zhi-hui |last3=Lin |first3=Ying |last4=Chen |first4=Ni |last5=Gong |first5=Yue-jiao |last6=Zhong |first6=Jing-hui |last7=Chung |first7=Henry S.H. |last8=Li |first8=Yun |last9=Shi |first9=Yu-hui |title=Evolutionary Computation Meets Machine Learning: A Survey |journal=Computational Intelligence Magazine |year=2011 |volume=6 |issue=4 |pages=68–75 |url=http://ieeexplore.ieee.org/iel5/10207/6052357/06052374.pdf?arnumber=6052374 }}</ref>。
<ref>{{cite journal |last1=Zhang |first1=Jun |last2=Zhan |first2=Zhi-hui |last3=Lin |first3=Ying |last4=Chen |first4=Ni |last5=Gong |first5=Yue-jiao |last6=Zhong |first6=Jing-hui |last7=Chung |first7=Henry S.H. |last8=Li |first8=Yun |last9=Shi |first9=Yu-hui |title=Evolutionary Computation Meets Machine Learning: A Survey |journal=Computational Intelligence Magazine |year=2011 |volume=6 |issue=4 |pages=68–75 |url=http://ieeexplore.ieee.org/iel5/10207/6052357/06052374.pdf?arnumber=6052374 }}</ref>。
=== 训练模型 Training models ===
=== 训练模型 ===
通常情况下，机器学习模型需要大量的数据才能有良好的性能，因此当训练一个机器学习模型时，需要从一个训练集中收集大量有代表性的数据样本。来自训练集的数据可以像文本语料库、图像集合和从服务的单个用户收集的数据一样多种多样。当训练一个机器学习模型时，需要特别注意过拟合问题。
通常情况下，机器学习模型需要大量的数据才能有良好的性能，因此当训练一个机器学习模型时，需要从一个训练集中收集大量有代表性的数据样本。来自训练集的数据可以像文本语料库、图像集合和从服务的单个用户收集的数据一样多种多样。当训练一个机器学习模型时，需要特别注意过拟合问题。
==== 联合学习 Federated learning ====
==== 联合学习 ====
'''联合学习 Federated Learning'''是一种新的训练机器学习模型的方法，它分散了训练的过程，允许用户不需要将他们的数据发送到一个集中的服务器这样的做法来维护他们的隐私。通过将模型的训练过程分散到许多设备上，提升了算法效率。例如，谷歌董事会使用联合机器学习刚发来训练用户手机上的搜索查询预测模型，而不必将每个人地搜索信息发送回谷歌。<ref>{{Cite web|url=http://ai.googleblog.com/2017/04/federated-learning-collaborative.html|title=Federated Learning: Collaborative Machine Learning without Centralized Training Data|website=Google AI Blog|language=en|access-date=2019-06-08}}</ref>
'''联合学习 Federated Learning'''是一种新的训练机器学习模型的方法，它分散了训练的过程，允许用户不需要将他们的数据发送到一个集中的服务器这样的做法来维护他们的隐私。通过将模型的训练过程分散到许多设备上，提升了算法效率。例如，谷歌董事会使用联合机器学习刚发来训练用户手机上的搜索查询预测模型，而不必将每个人地搜索信息发送回谷歌。<ref>{{Cite web|url=http://ai.googleblog.com/2017/04/federated-learning-collaborative.html|title=Federated Learning: Collaborative Machine Learning without Centralized Training Data|website=Google AI Blog|language=en|access-date=2019-06-08}}</ref>