Error-backpropagation in temporally encoded networks of spiking neurons
Error-backpropagation in temporally encoded networks of spiking neurons
复制标题
DOI：
10.1016/s0925-2312(01)00658-0
复制
发表时间：
2002-10-01
期刊：
影响因子：
6
通讯作者：
La Poutré, H
中科院分区：
文献类型：
--
作者：
Bohte, SM;Kok, JN;La Poutré, H
对于一个网络的尖峰神经元，编码信息的时间的个人尖峰时间，我们得到一个监督学习规则，SpikeProp，类似于传统的错误反向传播。有了这个算法，我们演示了如何与生物合理的动作电位尖峰神经元网络可以执行复杂的非线性分类，在快速的时间编码，以及速率编码的网络。我们进行实验的经典XOR问题时，提出了一个时间设置，以及其他一些基准数据集。比较内插XOR问题的编码所需的尖峰神经元的（隐式）数量，经训练的网络表明，时间编码是快速神经信息处理的可行代码，因此需要比瞬时速率编码更少的神经元。此外，我们发现，可靠的时间计算的尖峰网络时，才完成使用尖峰响应函数的时间常数长于编码间隔，已预测的理论考虑。(C)2002 Elsevier Science B.V.保留所有权利。
For a network of spiking neurons that encodes information in the timing of individual spike times, we derive a supervised learning rule, SpikeProp, akin to traditional error-backpropagation. With this algorithm, we demonstrate how networks of spiking neurons with biologically reasonable action potentials can perform complex non-linear classification in fast temporal coding just as well as rate-coded networks. We perform experiments for the classical XOR problem, when posed in a temporal setting, as well as for a number of other benchmark datasets. Comparing the (implicit) number of spiking neurons required for the encoding of the interpolated XOR problem, the trained networks demonstrate that temporal coding is a viable code for fast neural information processing, and as such requires less neurons than instantaneous rate-coding. Furthermore, we find that reliable temporal computation in the spiking networks was only accomplished when using spike response functions with a time constant longer than the coding interval, as has been predicted by theoretical considerations. (C) 2002 Elsevier Science B.V. All rights reserved.