Drawing inspiration from biological dendrites to empower artificial neural networks Spyridon Chavlis and Panayiota Poirazi
Drawing inspiration from biological dendrites to empower artificial neural networks Spyridon Chavlis and Panayiota Poirazi
复制标题
DOI：
10.1016/j.conb.2021.04.007
复制
发表时间：
2021-10-01
影响因子：
5.7
通讯作者：
Poirazi，Panayiota
中科院分区：
文献类型：
--
作者：
Chavlis，Spyridon;Poirazi，Panayiota
本文重点介绍了生物神经元及其树突树的具体特征，这些特征的采用可能有助于推进各种机器学习应用中使用的人工神经网络。进步可以采取增加计算能力和/或降低功耗的形式。提出的功能包括树突解剖，树突非线性和分区可塑性规则，所有这些都塑造了生物网络中的学习和信息处理。我们讨论了这些特征在生物神经元中提供的计算优势，并提出了在人工神经元中采用它们的方法，以利用机器学习中的相应优势。
This article highlights specific features of biological neurons and their dendritic trees, whose adoption may help advance artificial neural networks used in various machine learning applications. Advancements could take the form of increased computational capabilities and/or reduced power consumption. Proposed features include dendritic anatomy, dendritic nonlinearities, and compartmentalized plasticity rules, all of which shape learning and information processing in biological networks. We discuss the computational benefits provided by these features in biological neurons and suggest ways to adopt them in artificial neurons in order to exploit the respective benefits in machine learning.