43
个编辑
更改
跳到导航
跳到搜索
第5行：
第5行： − + − Neuromorphic engineering, also known as neuromorphic computing, is the use of very-large-scale integration (VLSI) systems containing electronic analog circuits to mimic neuro-biological architectures present in the nervous system. A neuromorphic computer/chip is any device that uses physical artificial neurons (made from silicon) to do computations. In recent times, the term neuromorphic has been used to describe analog, digital, mixed-mode analog/digital VLSI, and software systems that implement models of neural systems (for perception, motor control, or multisensory integration). The implementation of neuromorphic computing on the hardware level can be realized by oxide-based memristors, spintronic memories, threshold switches, and transistors. Training software-based neuromorphic systems of spiking neural networks can be achieved using error backpropagation, e.g., using Python based frameworks such as snnTorch, or using canonical learning rules from the biological learning literature, e.g., using BindsNet. − + − A key aspect of neuromorphic engineering is understanding how the morphology of individual neurons, circuits, applications, and overall architectures creates desirable computations, affects how information is represented, influences robustness to damage, incorporates learning and development, adapts to local change (plasticity), and facilitates evolutionary change. − + − Neuromorphic engineering is an interdisciplinary subject that takes inspiration from biology, physics, mathematics, computer science, and electronic engineering to design artificial neural systems, such as vision systems, head-eye systems, auditory processors, and autonomous robots, whose physical architecture and design principles are based on those of biological nervous systems. It was developed by Carver Mead in the late 1980s. − +
无编辑摘要
{{Use mdy dates|date = January 2019}}
{{Use mdy dates|date = January 2019}}
'''Neuromorphic engineering''', also known as '''neuromorphic computing''',<ref>{{Cite journal | doi = 10.1145/2601069| title = Neuromorphic computing gets ready for the (really) big time| journal = [[Communications of the ACM]]| volume = 57| issue = 6| year = 2014| last1 = Monroe | first1 = D. | pages = 13–15| s2cid = 20051102}}</ref><ref>{{Cite journal | doi = 10.1088/0957-4484/21/17/175202| pmid = 20368686| title = Nanotube devices based crossbar architecture: Toward neuromorphic computing| journal = Nanotechnology| volume = 21| issue = 17| pages = 175202| year = 2010| last1 = Zhao | first1 = W. S. | last2 = Agnus | first2 = G. | last3 = Derycke | first3 = V. | last4 = Filoramo | first4 = A. | last5 = Bourgoin | first5 = J. -P. | last6 = Gamrat | first6 = C. | bibcode = 2010Nanot..21q5202Z| url = https://zenodo.org/record/3428659}}</ref><ref name="humanbrainproject">{{YouTube|id=6RoiZ90mGfw|title=The Human Brain Project SP 9: Neuromorphic Computing Platform}}</ref> is the use of [[very-large-scale integration]] (VLSI) systems containing electronic [[analog circuit]]s to mimic neuro-biological architectures present in the nervous system. A neuromorphic computer/chip is any device that uses physical artificial neurons (made from silicon) to do computations.<ref>{{cite journal|last1=Mead|first1=Carver|title=Neuromorphic electronic systems|journal=Proceedings of the IEEE|date=1990|volume=78|issue=10|pages=1629–1636|doi=10.1109/5.58356|url=https://authors.library.caltech.edu/53090/1/00058356.pdf}}</ref><ref name=":2" /> In recent times, the term ''neuromorphic'' has been used to describe analog, digital, mixed-mode analog/digital VLSI, and software systems that implement models of [[neural system]]s (for [[perception]], [[motor control]], or [[multisensory integration]]). The implementation of neuromorphic computing on the hardware level can be realized by oxide-based [[memristor]]s,<ref name="Maan 1–13">{{Cite journal|last1=Maan|first1=A. K.|last2=Jayadevi|first2=D. A.|last3=James|first3=A. P.|date=2016-01-01|title=A Survey of Memristive Threshold Logic Circuits|journal=IEEE Transactions on Neural Networks and Learning Systems|volume=PP|issue=99|pages=1734–1746|doi=10.1109/TNNLS.2016.2547842|pmid=27164608|issn=2162-237X|arxiv=1604.07121|bibcode=2016arXiv160407121M|s2cid=1798273}}</ref> spintronic memories, threshold switches, and [[transistor]]s.<ref>{{Cite journal|title = Mott Memory and Neuromorphic Devices|journal = Proceedings of the IEEE|date = 2015-08-01|issn = 0018-9219|pages = 1289–1310|volume = 103|issue = 8|doi = 10.1109/JPROC.2015.2431914|first1 = You|last1 = Zhou|first2 = S.|last2 = Ramanathan|s2cid = 11347598|url = https://zenodo.org/record/895565}}</ref><ref name=":2">{{Cite document|title=Neuromorphic Circuits With Neural Modulation Enhancing the Information Content of Neural Signaling {{!}} International Conference on Neuromorphic Systems 2020|language=EN|doi=10.1145/3407197.3407204|s2cid=220794387}}</ref> Training software-based neuromorphic systems of spiking neural networks can be achieved using error backpropagation, e.g., using [[Python (programming language)|Python]] based frameworks such as snnTorch,<ref>{{cite journal |last1=Eshraghian|first1=Jason K.|last2=Ward|first2=Max|last3=Neftci |first3=Emre|last4=Wang|first4=Xinxin|last5=Lenz|first5=Gregor|last6=Dwivedi|first6=Girish|last7=Bennamoun|first7=Mohammed|last8=Jeong|first8=Doo Seok|last9=Lu|first9=Wei D.|title=Training Spiking Neural Networks Using Lessons from Deep Learning |date=1 October 2021 |arxiv=2109.12894 }}</ref> or using canonical learning rules from the biological learning literature, e.g., using BindsNet.<ref>{{Cite web | url=https://github.com/Hananel-Hazan/bindsnet | title=Hananel-Hazan/bindsnet: Simulation of spiking neural networks (SNNs) using PyTorch.| date=31 March 2020}}</ref>
'''Neuromorphic engineering''', also known as '''neuromorphic computing''',<ref name=":3">{{Cite journal | doi = 10.1145/2601069| title = Neuromorphic computing gets ready for the (really) big time| journal = [[Communications of the ACM]]| volume = 57| issue = 6| year = 2014| last1 = Monroe | first1 = D. | pages = 13–15| s2cid = 20051102}}</ref><ref name=":4">{{Cite journal | doi = 10.1088/0957-4484/21/17/175202| pmid = 20368686| title = Nanotube devices based crossbar architecture: Toward neuromorphic computing| journal = Nanotechnology| volume = 21| issue = 17| pages = 175202| year = 2010| last1 = Zhao | first1 = W. S. | last2 = Agnus | first2 = G. | last3 = Derycke | first3 = V. | last4 = Filoramo | first4 = A. | last5 = Bourgoin | first5 = J. -P. | last6 = Gamrat | first6 = C. | bibcode = 2010Nanot..21q5202Z| url = https://zenodo.org/record/3428659}}</ref><ref name="humanbrainproject">{{YouTube|id=6RoiZ90mGfw|title=The Human Brain Project SP 9: Neuromorphic Computing Platform}}</ref> is the use of [[very-large-scale integration]] (VLSI) systems containing electronic [[analog circuit]]s to mimic neuro-biological architectures present in the nervous system. A neuromorphic computer/chip is any device that uses physical artificial neurons (made from silicon) to do computations.<ref name=":5">{{cite journal|last1=Mead|first1=Carver|title=Neuromorphic electronic systems|journal=Proceedings of the IEEE|date=1990|volume=78|issue=10|pages=1629–1636|doi=10.1109/5.58356|url=https://authors.library.caltech.edu/53090/1/00058356.pdf}}</ref><ref name=":2" /> In recent times, the term ''neuromorphic'' has been used to describe analog, digital, mixed-mode analog/digital VLSI, and software systems that implement models of [[neural system]]s (for [[perception]], [[motor control]], or [[multisensory integration]]). The implementation of neuromorphic computing on the hardware level can be realized by oxide-based [[memristor]]s,<ref name="Maan 1–13">{{Cite journal|last1=Maan|first1=A. K.|last2=Jayadevi|first2=D. A.|last3=James|first3=A. P.|date=2016-01-01|title=A Survey of Memristive Threshold Logic Circuits|journal=IEEE Transactions on Neural Networks and Learning Systems|volume=PP|issue=99|pages=1734–1746|doi=10.1109/TNNLS.2016.2547842|pmid=27164608|issn=2162-237X|arxiv=1604.07121|bibcode=2016arXiv160407121M|s2cid=1798273}}</ref> spintronic memories, threshold switches, and [[transistor]]s.<ref name=":6">{{Cite journal|title = Mott Memory and Neuromorphic Devices|journal = Proceedings of the IEEE|date = 2015-08-01|issn = 0018-9219|pages = 1289–1310|volume = 103|issue = 8|doi = 10.1109/JPROC.2015.2431914|first1 = You|last1 = Zhou|first2 = S.|last2 = Ramanathan|s2cid = 11347598|url = https://zenodo.org/record/895565}}</ref><ref name=":2">{{Cite document|title=Neuromorphic Circuits With Neural Modulation Enhancing the Information Content of Neural Signaling {{!}} International Conference on Neuromorphic Systems 2020|language=EN|doi=10.1145/3407197.3407204|s2cid=220794387}}</ref> Training software-based neuromorphic systems of spiking neural networks can be achieved using error backpropagation, e.g., using [[Python (programming language)|Python]] based frameworks such as snnTorch,<ref name=":7">{{cite journal |last1=Eshraghian|first1=Jason K.|last2=Ward|first2=Max|last3=Neftci |first3=Emre|last4=Wang|first4=Xinxin|last5=Lenz|first5=Gregor|last6=Dwivedi|first6=Girish|last7=Bennamoun|first7=Mohammed|last8=Jeong|first8=Doo Seok|last9=Lu|first9=Wei D.|title=Training Spiking Neural Networks Using Lessons from Deep Learning |date=1 October 2021 |arxiv=2109.12894 }}</ref> or using canonical learning rules from the biological learning literature, e.g., using BindsNet.<ref name=":8">{{Cite web | url=https://github.com/Hananel-Hazan/bindsnet | title=Hananel-Hazan/bindsnet: Simulation of spiking neural networks (SNNs) using PyTorch.| date=31 March 2020}}</ref>
'''<font color="#ff8000">神经形态工程Neuromorphic engineering</font>'''(也称为'''<font color="#ff8000">神经形态计算Neuromorphic computing</font>''')是指使用包含电子'''<font color="#ff8000">模拟电路Analog circuit</font>'''的'''<font color="#ff8000">超大规模集成电路Very-large-scale integration</font>'''系统来模拟神经系统中生理结构的研究方法。神经形态计算机或神经形态芯片包括任何使用由硅制成的人造神经元进行计算的设备。近年来，神经形态学（neuromorphic）这个术语被用来描述能够实现'''<font color="#ff8000">神经系统Neural system</font>'''模型功能(如'''<font color="#ff8000">感知Perception</font>'''、'''<font color="#ff8000">运动控制Motor control</font>'''，'''<font color="#ff8000">多感官整合Multisensory integration</font>'''等)的模拟、数字、模拟/数字混合模式超大规模集成电路和软件系统。神经形态计算的硬件实现可以通过基于氧化物的'''<font color="#ff8000">记忆电阻器Memristor</font>'''、自旋电子存储器、阈值开关和'''<font color="#ff8000">晶体管Transistor</font>'''来实现。对基于软件的脉冲神经网络系统的训练可以通过误差反向传播机制来实现，例如，使用snnTorch等基于Python的框架，或使用BindsNet等典型的受生物启发的学习模式。
'''<font color="#ff8000">神经形态工程Neuromorphic engineering</font>'''(也称为'''<font color="#ff8000">神经形态计算Neuromorphic computing</font>''')<ref name=":3" /><ref name=":4" /><ref name="humanbrainproject" />是指使用包含电子'''<font color="#ff8000">模拟电路Analog circuit</font>'''的'''<font color="#ff8000">超大规模集成电路Very-large-scale integration</font>'''系统来模拟神经系统中生理结构的研究方法。神经形态计算机或神经形态芯片包括任何使用由硅制成的人造神经元进行计算的设备。<ref name=":5" /><ref name=":2" />近年来，神经形态学（neuromorphic）这个术语被用来描述能够实现'''<font color="#ff8000">神经系统Neural system</font>'''模型功能(如'''<font color="#ff8000">感知Perception</font>'''、'''<font color="#ff8000">运动控制Motor control</font>'''，'''<font color="#ff8000">多感官整合Multisensory integration</font>'''等)的模拟、数字、模拟/数字混合模式超大规模集成电路和软件系统。神经形态计算的硬件实现可以通过基于氧化物的'''<font color="#ff8000">记忆电阻器Memristor</font>'''、<ref name="Maan 1–13" />自旋电子存储器、阈值开关和'''<font color="#ff8000">晶体管Transistor</font>'''来实现。<ref name=":6" /><ref name=":2" />对基于软件的脉冲神经网络系统的训练可以通过误差反向传播机制来实现，例如，使用snnTorch等基于Python的框架，<ref name=":7" />或使用BindsNet等典型的受生物启发的学习模式。<ref name=":8" />
A key aspect of neuromorphic engineering is understanding how the morphology of individual neurons, circuits, applications, and overall architectures creates desirable computations, affects how information is represented, influences robustness to damage, incorporates learning and development, adapts to local change (plasticity), and facilitates evolutionary change.
A key aspect of neuromorphic engineering is understanding how the morphology of individual neurons, circuits, applications, and overall architectures creates desirable computations, affects how information is represented, influences robustness to damage, incorporates learning and development, adapts to local change (plasticity), and facilitates evolutionary change.
神经形态工程领域的一个关键问题，就是理解'''<font color="#32CD32">单个神经元形态、神经回路、应用和整体结构</font>'''如何产生理想的计算，如何影响信息的表示和对破坏的鲁棒性，如何整合学习和发展，如何适应局部变化(可塑性) 并促进逐渐发展的变化。
神经形态工程领域的一个关键问题，就是理解'''<font color="#32CD32">单个神经元形态、神经回路、应用和整体结构</font>'''如何产生理想的计算，如何影响信息的表示和对破坏的鲁棒性，如何整合学习和发展，如何适应局部变化(可塑性) 并促进逐渐发展的变化。
Neuromorphic engineering is an interdisciplinary subject that takes inspiration from [[biology]], [[physics]], [[mathematics]], [[computer science]], and [[electronic engineering]]<ref name=":2" /> to design artificial neural systems, such as [[Machine vision|vision systems]], head-eye systems, auditory processors, and autonomous robots, whose physical architecture and design principles are based on those of biological nervous systems.<ref>{{Cite journal | doi = 10.1155/2012/705483| title = Qualitative Functional Decomposition Analysis of Evolved Neuromorphic Flight Controllers| journal = Applied Computational Intelligence and Soft Computing| volume = 2012| pages = 1–21| year = 2012| last1 = Boddhu | first1 = S. K. | last2 = Gallagher | first2 = J. C. | doi-access = free}}</ref> It was developed by [[Carver Mead]]<ref>{{cite web|title=carver mead website|last1=Mead|first1=Carver|url=http://www.carvermead.caltech.edu/index.html|website=carvermead}}</ref> in the late 1980s.
Neuromorphic engineering is an interdisciplinary subject that takes inspiration from [[biology]], [[physics]], [[mathematics]], [[computer science]], and [[electronic engineering]]<ref name=":2" /> to design artificial neural systems, such as [[Machine vision|vision systems]], head-eye systems, auditory processors, and autonomous robots, whose physical architecture and design principles are based on those of biological nervous systems.<ref name=":9">{{Cite journal | doi = 10.1155/2012/705483| title = Qualitative Functional Decomposition Analysis of Evolved Neuromorphic Flight Controllers| journal = Applied Computational Intelligence and Soft Computing| volume = 2012| pages = 1–21| year = 2012| last1 = Boddhu | first1 = S. K. | last2 = Gallagher | first2 = J. C. | doi-access = free}}</ref> It was developed by [[Carver Mead]]<ref name=":10">{{cite web|title=carver mead website|last1=Mead|first1=Carver|url=http://www.carvermead.caltech.edu/index.html|website=carvermead}}</ref> in the late 1980s.
神经形态工程是以'''<font color="#ff8000">生物学Biology</font>'''、'''<font color="#ff8000">物理学Physics</font>'''、'''<font color="#ff8000">数学Mathematics</font>'''、'''<font color="#ff8000">计算机科学Computer science</font>'''和'''<font color="#ff8000">电子工程Electronic engineering</font>'''等学科为基础，设计人工神经系统（如'''<font color="#ff8000">视觉系统Vision systems</font>'''、头眼系统、听觉处理器以及物理结构和设计原则都受启发于生物神经系统的自主机器人）的一门交叉学科。20世纪80年代后期，卡弗·米德极大地推动了神经形态工程领域的发展。
神经形态工程是以'''<font color="#ff8000">生物学Biology</font>'''、'''<font color="#ff8000">物理学Physics</font>'''、'''<font color="#ff8000">数学Mathematics</font>'''、'''<font color="#ff8000">计算机科学Computer science</font>'''和'''<font color="#ff8000">电子工程Electronic engineering<ref name=":2" /></font>'''等学科为基础，设计人工神经系统（如'''<font color="#ff8000">视觉系统Vision systems</font>'''、头眼系统、听觉处理器以及物理结构和设计原则都受启发于生物神经系统的自主机器人）的一门交叉学科。<ref name=":9" />20世纪80年代后期，卡弗·米德极大地推动了神经形态工程领域的发展。<ref name=":10" />
==Neurological inspiration==
==Neurological inspiration==