138
个编辑
更改
无编辑摘要
==概述==
==概述==
神经形态工程 Neuromorphic engineering（也称为神经形态计算 Neuromorphic computing或类脑计算 Brain-inspired computing）。<ref>Monroe, D. (2014). "Neuromorphic computing gets ready for the (really) big time". Communications of the ACM. 57 (6): 13–15. doi:[https://datascienceassn.org/sites/default/files/Neuromorphic%20Computing%20Ready%20for%20Big%20Time.pdf 10.1145/2601069].</ref><ref>Zhao, W. S.; Agnus, G.; Derycke, V.; Filoramo, A.; Bourgoin, J. -P.; Gamrat, C. (2010). "Nanotube devices based crossbar architecture: Toward neuromorphic computing". Nanotechnology. 21 (17): 175202. Bibcode:2010Nanot..21q5202Z. doi:10.1088/0957-4484/21/17/175202. <nowiki>PMID 20368686</nowiki>.</ref><ref>The Human Brain Project SP 9: Neuromorphic Computing Platform on YouTube</ref>
神经形态工程 Neuromorphic engineering（也称为神经形态计算 Neuromorphic computing或类脑计算 Brain-inspired computing）。<ref>Monroe, D. (2014). "[https://datascienceassn.org/sites/default/files/Neuromorphic%20Computing%20Ready%20for%20Big%20Time.pdf Neuromorphic computing gets ready for the (really) big time]". Communications of the ACM. 57 (6): 13–15. doi:[https://datascienceassn.org/sites/default/files/Neuromorphic%20Computing%20Ready%20for%20Big%20Time.pdf 10.1145/2601069].</ref><ref>Zhao, W. S.; Agnus, G.; Derycke, V.; Filoramo, A.; Bourgoin, J. -P.; Gamrat, C. (2010). "Nanotube devices based crossbar architecture: Toward neuromorphic computing". Nanotechnology. 21 (17): 175202. Bibcode:2010Nanot..21q5202Z. doi:10.1088/0957-4484/21/17/175202. <nowiki>PMID 20368686</nowiki>.</ref><ref>The Human Brain Project SP 9: Neuromorphic Computing Platform on YouTube</ref>
是指使用包含电子模拟电路的超大规模集成电路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>Mead, Carver (1990). "Neuromorphic electronic systems" (PDF). Proceedings of the IEEE. 78 (10): 1629–1636. doi:10.1109/5.58356.</ref><ref name=":0">"Neuromorphic Circuits With Neural Modulation Enhancing the Information Content of Neural Signaling | International Conference on Neuromorphic Systems 2020" (in English). doi:10.1145/3407197.3407204.</ref>近年来，神经形态学 neuromorphic被用来描述能够实现神经系统模型功能（如感知、运动控制，多感官整合等）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记忆电阻器 Memristor（简称忆阻器）、自旋电子存储器、阈值开关和晶体管来实现。<ref name=":0" /><ref>Zhou, You; Ramanathan, S. (2015-08-01). "Mott Memory and Neuromorphic Devices". Proceedings of the IEEE. 103 (8): 1289–1310. doi:10.1109/JPROC.2015.2431914. ISSN 0018-9219.</ref>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>Eshraghian, Jason K.; Ward, Max; Neftci, Emre; Wang, Xinxin; Lenz, Gregor; Dwivedi, Girish; Bennamoun, Mohammed; Jeong, Doo Seok; Lu, Wei D. (1 October 2021). "Training Spiking Neural Networks Using Lessons from Deep Learning". arXiv:2109.12894.</ref>，或使用BindsNet等典型的受生物启发的学习模式<ref>"Hananel-Hazan/bindsnet: Simulation of spiking neural networks (SNNs) using PyTorch". 31 March 2020.</ref>。
是指使用包含电子模拟电路的超大规模集成电路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>Mead, Carver (1990). "Neuromorphic electronic systems" (PDF). Proceedings of the IEEE. 78 (10): 1629–1636. doi:10.1109/5.58356.</ref><ref name=":0">"Neuromorphic Circuits With Neural Modulation Enhancing the Information Content of Neural Signaling | International Conference on Neuromorphic Systems 2020" (in English). doi:10.1145/3407197.3407204.</ref>近年来，神经形态学 neuromorphic被用来描述能够实现神经系统模型功能（如感知、运动控制，多感官整合等）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记忆电阻器 Memristor（简称忆阻器）、自旋电子存储器、阈值开关和晶体管来实现。<ref name=":0" /><ref>Zhou, You; Ramanathan, S. (2015-08-01). "Mott Memory and Neuromorphic Devices". Proceedings of the IEEE. 103 (8): 1289–1310. doi:10.1109/JPROC.2015.2431914. ISSN 0018-9219.</ref>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>Eshraghian, Jason K.; Ward, Max; Neftci, Emre; Wang, Xinxin; Lenz, Gregor; Dwivedi, Girish; Bennamoun, Mohammed; Jeong, Doo Seok; Lu, Wei D. (1 October 2021). "Training Spiking Neural Networks Using Lessons from Deep Learning". arXiv:2109.12894.</ref>，或使用BindsNet等典型的受生物启发的学习模式<ref>"Hananel-Hazan/bindsnet: Simulation of spiking neural networks (SNNs) using PyTorch". 31 March 2020.</ref>。