An Introduction to Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
This work provides an introductory framework for SNNs, which could benefit researchers in neuromorphic computing by offering energy-efficient alternatives to conventional neural networks, though it is incremental as it builds on existing probabilistic models.
The paper introduces Spiking Neural Networks (SNNs) by developing a probabilistic signal processing methodology to derive learning rules that leverage their time encoding capabilities, resulting in supervised and unsupervised learning rules derived from first principles using variational inference.
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.