SPAN: SPIKE PATTERN ASSOCIATION NEURON FOR LEARNING SPATIO-TEMPORAL SPIKE PATTERNS

TLDR

Spiking neural networks can process spatio‑temporal information, yet designing efficient supervised learning algorithms for them remains challenging. The study introduces SPAN, a neuron that learns supervised associations of arbitrary spike trains to capture precise spike‑timing information. SPAN converts spike trains into analog signals during training, enabling the Widrow‑Hoff rule to adjust synaptic weights and is evaluated for learning, memory, noise robustness, and classification performance.

Abstract

Spiking Neural Networks (SNN) were shown to be suitable tools for the processing of spatio-temporal information. However, due to their inherent complexity, the formulation of efficient supervised learning algorithms for SNN is difficult and remains an important problem in the research area. This article presents SPAN - a spiking neuron that is able to learn associations of arbitrary spike trains in a supervised fashion allowing the processing of spatio-temporal information encoded in the precise timing of spikes. The idea of the proposed algorithm is to transform spike trains during the learning phase into analog signals so that common mathematical operations can be performed on them. Using this conversion, it is possible to apply the well-known Widrow-Hoff rule directly to the transformed spike trains in order to adjust the synaptic weights and to achieve a desired input/output spike behavior of the neuron. In the presented experimental analysis, the proposed learning algorithm is evaluated regarding its learning capabilities, its memory capacity, its robustness to noisy stimuli and its classification performance. Differences and similarities of SPAN regarding two related algorithms, ReSuMe and Chronotron, are discussed.