期刊
PHYSICAL REVIEW LETTERS
卷 105, 期 21, 页码 -出版社
AMER PHYSICAL SOC
DOI: 10.1103/PhysRevLett.105.218102
关键词
-
资金
- French Foreign Ministry
- Israel Science Foundation
- Israeli Defense Ministry
- ANR [06 JCJC-051]
We study the computational capacity of a model neuron, the tempotron, which classifies sequences of spikes by linear-threshold operations. We use statistical mechanics and extreme value theory to derive the capacity of the system in random classification tasks. In contrast with its static analog, the perceptron, the tempotron's solutions space consists of a large number of small clusters of weight vectors. The capacity of the system per synapse is finite in the large size limit and weakly diverges with the stimulus duration relative to the membrane and synaptic time constants.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据