Response Function and Training Method to Improve Response to Successive Input Patterns in SpikeProp

Abstract

In this paper, we aim to improve the response to successive input patterns in SpikeProp, which is a kind of spiking neural networks. We proposed two methods: (1) change the spike response function, which decides network behavior, and (2) train combined patterns. The response was improved by using both methods. Concretely, we got 70% of success rate for successive inputs on the network trained by proposed methods in the case that the network trained by the previous method failed.