Parra Lucas C, Beck Jeffrey M, Bell Anthony J
Biomedical Engineering Department, City College of New York, New York, NY 10033, USA.
Neural Comput. 2009 Nov;21(11):2991-3009. doi: 10.1162/neco.2009.04-06-184.
A feedforward spiking network represents a nonlinear transformation that maps a set of input spikes to a set of output spikes. This mapping transforms the joint probability distribution of incoming spikes into a joint distribution of output spikes. We present an algorithm for synaptic adaptation that aims to maximize the entropy of this output distribution, thereby creating a model for the joint distribution of the incoming point processes. The learning rule that is derived depends on the precise pre- and postsynaptic spike timings. When trained on correlated spike trains, the network learns to extract independent spike trains, thereby uncovering the underlying statistical structure and creating a more efficient representation of the incoming spike trains.
前馈脉冲神经网络表示一种非线性变换，它将一组输入脉冲映射为一组输出脉冲。这种映射将输入脉冲的联合概率分布转换为输出脉冲的联合分布。我们提出了一种突触适应算法，旨在最大化该输出分布的熵，从而创建一个用于输入点过程联合分布的模型。推导得出的学习规则取决于精确的突触前和突触后脉冲时间。当在相关脉冲序列上进行训练时，该网络学会提取独立的脉冲序列，从而揭示潜在的统计结构，并创建输入脉冲序列的更有效表示。
