期刊
FRONTIERS IN COMPUTATIONAL NEUROSCIENCE
卷 14, 期 -, 页码 -出版社
FRONTIERS MEDIA SA
DOI: 10.3389/fncom.2020.00033
关键词
compartmental modeling; non-linear dendrites; cortical excitatory synapses; single neuron computation; machine learning; synaptic weights; dendritic voltage attenuation; perceptron
资金
- EU Horizon 2020 program [720270]
- Huawei Technologies Co., Ltd.
- Gatsby Charitable Foundation
- ETH
- NIH [U01MH114812]
- Drahi family foundation
The perceptron learning algorithm and its multiple-layer extension, the backpropagation algorithm, are the foundations of the present-day machine learning revolution. However, these algorithms utilize a highly simplified mathematical abstraction of a neuron; it is not clear to what extent real biophysical neurons with morphologically-extended non-linear dendritic trees and conductance-based synapses can realize perceptron-like learning. Here we implemented the perceptron learning algorithm in a realistic biophysical model of a layer 5 cortical pyramidal cell with a full complement of non-linear dendritic channels. We tested this biophysical perceptron (BP) on a classification task, where it needed to correctly binarily classify 100, 1,000, or 2,000 patterns, and a generalization task, where it was required to discriminate between two noisy patterns. We show that the BP performs these tasks with an accuracy comparable to that of the original perceptron, though the classification capacity of the apical tuft is somewhat limited. We concluded that cortical pyramidal neurons can act as powerful classification devices.
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