SPA: Stochastic Probability Adjustment for System Balance of Unsupervised SNNs
This work addresses the problem of low performance in SNNs for researchers and practitioners in neuromorphic computing, though it appears incremental as it builds on existing SNN architectures.
The paper tackles the performance gap between spiking neural networks (SNNs) and artificial neural networks (ANNs) by proposing a Stochastic Probability Adjustment (SPA) system, which improves classification accuracy by 1.99% on MNIST and 6.29% on EMNIST in unsupervised SNN architectures.
Spiking neural networks (SNNs) receive widespread attention because of their low-power hardware characteristic and brain-like signal response mechanism, but currently, the performance of SNNs is still behind Artificial Neural Networks (ANNs). We build an information theory-inspired system called Stochastic Probability Adjustment (SPA) system to reduce this gap. The SPA maps the synapses and neurons of SNNs into a probability space where a neuron and all connected pre-synapses are represented by a cluster. The movement of synaptic transmitter between different clusters is modeled as a Brownian-like stochastic process in which the transmitter distribution is adaptive at different firing phases. We experimented with a wide range of existing unsupervised SNN architectures and achieved consistent performance improvements. The improvements in classification accuracy have reached 1.99% and 6.29% on the MNIST and EMNIST datasets respectively.