Supervised Learning in Multilayer Spiking Neural Networks

TL;DR

This paper presents a flexible supervised learning algorithm for multilayer spiking neural networks capable of handling multiple spikes and various neuron models, demonstrated on benchmark and complex classification tasks.

Contribution

It introduces a novel supervised learning algorithm applicable to neurons firing multiple spikes and any linearisable neuron model, overcoming limitations of previous methods.

Findings

Successfully applied to XOR and Iris benchmarks

Handles different spike timing encodings including precise spike trains

Demonstrates flexibility and effectiveness in complex classification tasks

Abstract

The current article introduces a supervised learning algorithm for multilayer spiking neural networks. The algorithm presented here overcomes some limitations of existing learning algorithms as it can be applied to neurons firing multiple spikes and it can in principle be applied to any linearisable neuron model. The algorithm is applied successfully to various benchmarks, such as the XOR problem and the Iris data set, as well as complex classifications problems. The simulations also show the flexibility of this supervised learning algorithm which permits different encodings of the spike timing patterns, including precise spike trains encoding.