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

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. Keywords: Stream learning, gaussian receptive fields, population encoding, spiking neural networks 1. Introduction The continuous production of tremendous amount of data in the form of fast streams upsets the traditional view in machine learning, thus giving rise to a new emerging paradigm called stream learning (SL). These streams of data evolve generally over time and may be occasionally affected by a change (concept drift) which impacts on their input data distribution, without following the fundamental hypothesis of stationarity upon which the learning theory is based. Learning in non-stationary environments has attracted much attention in the SL community in Corresponding author: jesus.lopez@tecnalia.com