.png){kind=icon}
返回
Meta-learning biologically plausible plasticity rules with random feedback pathways
.png){kind=icon}
OA
AI
DOI：10.1038/s41467-023-37562-1.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The biological plausibility of backpropagation and its relationship with synaptic plasticity remain open questions. The authors propose a meta-learning approach to discover interpretable plasticity rules to train neural networks under biological constraints. The meta-learned rules boost the learning efficiency via bio-inspired synaptic plasticity. Backpropagation is widely used to train artificial neural networks, but its relationship to synaptic plasticity in the brain is unknown. Some biological models of backpropagation rely on feedback projections that are symmetric with feedforward connections, but experiments do not corroborate the existence of such symmetric backward connectivity. Random feedback alignment offers an alternative model in which errors are propagated backward through fixed, random backward connections. This approach successfully trains shallow models, but learns slowly and does not perform well with deeper models or online learning. In this study, we develop a meta-learning approach to discover interpretable, biologically plausible plasticity rules that improve online learning performance with fixed random feedback connections. The resulting plasticity rules show improved online training of deep models in the low data regime. Our results highlight the potential of meta-learning to discover effective, interpretable learning rules satisfying biological constraints.
Keyword:
SENSITIVITY
PATTERNS
SPIKES
MODEL
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
15.7
论文数:
9.4W
被引数:
91.2W
机构
引用论文
分享收藏The dimesitylboron group in organic synthesis. 5. Hetero-atom substituted dimesitylborylmethanes.
PREAI
分享收藏The Alkaloid Compound Harmane Increases the Lifespan of Caenorhabditis elegans during Bacterial Infection, by Modulating the Nematode’s Innate Immune Response.png)
PLoS ONE
OAAI
PLoS ONEIF0
OAAI分享收藏
查看更多内容