.png){kind=icon}
返回
Random synaptic feedback weights support error backpropagation for deep learning
.png){kind=icon}
OA
AI
DOI：10.1038/ncomms13276.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The brain processes information through multiple layers of neurons. This deep architecture is representationally powerful, but complicates learning because it is difficult to identify the responsible neurons when a mistake is made. In machine learning, the backpropagation algorithm assigns blame by multiplying error signals with all the synaptic weights on each neuron's axon and further downstream. However, this involves a precise, symmetric backward connectivity pattern, which is thought to be impossible in the brain. Here we demonstrate that this strong architectural constraint is not required for effective error propagation. We present a surprisingly simple mechanism that assigns blame by multiplying errors by even random synaptic weights. This mechanism can transmit teaching signals across multiple layers of neurons and performs as effectively as backpropagation on a variety of tasks. Our results help reopen questions about how the brain could use error signals and dispel long-held assumptions about algorithmic constraints on learning.
Keyword:
VISUAL-CORTEX
REINFORCEMENT
PLASTICITY
REPRESENTATIONS
PREDICTION
CEREBELLUM
ACTIVATION
SIGN
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:
9.3W
被引数:
91.2W
机构
引用论文
分享收藏A cooperative switch determines the sign of synaptic plasticity in distal dendrites of neocortical pyramidal neurons.png)
NEURON
OAAI
NEURONIF15
OAAI分享收藏Variations of intramolecular ligation rates allow the detection of protein-induced bends in DNA.OAAI
OAAI分享收藏Study of bi-directional buck-boost converter topologies for application in electrical vehicle motor drives应用于电动汽车电机驱动的双向buck-boost变换器拓扑研究
PREAI
分享收藏Cerebellar long-term depression: Characterization, signal transduction, and functional rolesPHYSIOLOGICAL REVIEWS
PHYSIOLOGICAL REVIEWSIF28.7
PREAI
分享收藏
查看更多内容