An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications

TL;DR

This paper introduces probabilistic models and learning rules for Spiking Neural Networks, emphasizing their energy-efficient hardware implementations and direct training methods based on variational inference, highlighting open research challenges.

Contribution

It presents a probabilistic signal processing framework for SNNs, deriving new supervised and unsupervised learning rules directly from first principles.

Findings

Probabilistic models enable direct derivation of SNN learning rules.

Energy-efficient hardware implementations are facilitated by sparse spiking inputs.

Open research problems in SNNs are identified and discussed.

Abstract

Spiking Neural Networks (SNNs) are distributed trainable systems whose computing elements, or neurons, are characterized by internal analog dynamics and by digital and sparse synaptic communications. The sparsity of the synaptic spiking inputs and the corresponding event-driven nature of neural processing can be leveraged by hardware implementations that have demonstrated significant energy reductions as compared to conventional Artificial Neural Networks (ANNs). Most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pre-trained ANNs via rate encoding. This paper aims at providing an introduction to SNNs by focusing on a probabilistic signal processing methodology that enables the direct derivation of learning rules leveraging the unique time encoding capabilities of SNNs. To this end, the paper adopts discrete-time probabilistic models for networked spiking neurons, and it derives supervised and unsupervised learning rules from first principles by using variational inference. Examples and open research problems are also provided.