An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications
This work addresses the need for efficient training methods in SNNs, which are crucial for energy-efficient AI hardware, though it appears incremental as it builds on existing probabilistic models.
The paper tackles the lag in training algorithms for spiking neural networks (SNNs) compared to hardware advancements by introducing a probabilistic signal processing methodology that directly derives supervised and unsupervised learning rules 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 energy-efficient hardware implementations, which can offer significant energy reductions as compared to conventional artificial neural networks (ANNs). The design of training algorithms lags behind the hardware implementations. Most existing training algorithms for SNNs have been designed either for biological plausibility or through conversion from pretrained ANNs via rate encoding. This article provides an introduction to SNNs by focusing on a probabilistic signal processing methodology that enables the direct derivation of learning rules by leveraging the unique time-encoding capabilities of SNNs. We adopt discrete-time probabilistic models for networked spiking neurons and derive supervised and unsupervised learning rules from first principles via variational inference. Examples and open research problems are also provided.