Supervised learning in Spiking Neural Networks with Limited Precision: SNN/LP

TL;DR

This paper introduces SNN/LP, a supervised learning algorithm for Spiking Neural Networks that uses limited precision weights and delays, employing a genetic algorithm, with promising results for hardware implementation.

Contribution

The paper presents a novel supervised learning method for SNNs using limited precision and genetic algorithms, suitable for large-scale hardware neural networks.

Findings

Results are comparable or better than previous methods.

One trained network is successfully implemented in hardware.

Limited precision approach reduces complexity for hardware deployment.

Abstract

A new supervised learning algorithm, SNN/LP, is proposed for Spiking Neural Networks. This novel algorithm uses limited precision for both synaptic weights and synaptic delays; 3 bits in each case. Also a genetic algorithm is used for the supervised training. The results are comparable or better than previously published work. The results are applicable to the realization of large scale hardware neural networks. One of the trained networks is implemented in programmable hardware.