.png){kind=icon}
返回
Efficient supervised learning in networks with binary synapses
.png){kind=icon}
OA
AI
DOI：10.1073/pnas.0700324104.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Recent experimental studies indicate that synaptic changes induced by neuronal activity are discrete jumps between a small number of stable states. Learning in systems with discrete synapses is known to be a computationally hard problem. Here, we study a neurobiologically plausible on-line learning algorithm that derives from belief propagation algorithms. We show that it performs remarkably well in a model neuron with binary synapses, and a finite number of hidden states per synapse, that has to learn a random classification task. Such a system is able to learn a number of associations close to the theoretical limit in time that is sublinear in system size. This is to our knowledge the first on-line algorithm that is able to achieve efficiently a finite number of patterns learned per binary synapse. Furthermore, we show that performance is optimal for a finite number of hidden states that becomes very small for sparse coding. The algorithm is similar to the standard perceptron learning algorithm, with an additional rule for synaptic transitions that occur only if a currently presented pattern is barely correct. In this case, the synaptic changes are metaplastic only (change in hidden states and not in actual synaptic state), stabilizing the synapse in its current state. Finally, we show that a system with two visible states and K hidden states is much more robust to noise than a system with K visible states. We suggest that this rule is sufficiently simple to be easily implemented by neurobiological systems or in hardware.
Keyword:
belief propagation
computational neuroscience
perceptron
synaptic plasticity
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
P
IF:
9.1
论文数:
10.8W
被引数:
73.5W
机构
暂无机构信息
引用论文
Electrochromic Devices Based on Poly(2,6-di(9H-carbazol-9-yl)pyridine)-Type Polymer Films and PEDOT-PSS.png)
PolymersOAAI
PolymersIF0
OAAI分享收藏Bistability in the Ca2+/calmodulin-dependent protein kinase-phosphatase systemBIOPHYSICAL JOURNALOAAI
BIOPHYSICAL JOURNALIF3.1
OAAI分享收藏Long-term records of cadmium and silver contamination in sediments and oysters from the Gironde fluvial–estuarine continuum – Evidence of changing silver sourcesChemosphereOAAI
ChemosphereIF0
OAAI分享收藏A Novel Modelling Approach for Predicting Forest Growth and Yield under Climate ChangePLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Molecular identification of white morphotype strains of endophytic fungi from Pinus tabulaeformis
PREAI
分享收藏分享收藏
查看更多内容