Exploiting a Stimuli Encoding Scheme of Spiking Neural Networks for Stream Learning

TL;DR

This paper investigates the use of Gaussian receptive fields as a pre-processing encoding scheme for spiking neural networks in stream learning, demonstrating improved predictive performance across synthetic and real datasets.

Contribution

It introduces a novel application of Gaussian receptive fields as a general pre-processing method to enhance spiking neural network stream learning.

Findings

Effective pre-processing technique for stream data

Improved predictive accuracy in experiments

Applicable to various datasets

Abstract

Stream data processing has gained progressive momentum with the arriving of new stream applications and big data scenarios. One of the most promising techniques in stream learning is the Spiking Neural Network, and some of them use an interesting population encoding scheme to transform the incoming stimuli into spikes. This study sheds lights on the key issue of this encoding scheme, the Gaussian receptive fields, and focuses on applying them as a pre-processing technique to any dataset in order to gain representativeness, and to boost the predictive performance of the stream learning methods. Experiments with synthetic and real data sets are presented, and lead to confirm that our approach can be applied successfully as a general pre-processing technique in many real cases.