Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks
This provides a tool for machine learning, neuromorphic intelligence, and computational neuroscience researchers, but it is incremental as it builds on existing SNN models by incorporating noise.
The study tackled the problem of deterministic models in spiking neural networks (SNNs) overlooking neural noise by introducing noisy spiking neural networks (NSNNs) and a noise-driven learning rule, resulting in competitive performance, improved robustness against perturbations, and better reproduction of probabilistic computations.
$\textbf{Formal version available at}$ https://cell.com/patterns/fulltext/S2666-3899(23)00200-3 Networks of spiking neurons underpin the extraordinary information-processing capabilities of the brain and have become pillar models in neuromorphic artificial intelligence. Despite extensive research on spiking neural networks (SNNs), most studies are established on deterministic models, overlooking the inherent non-deterministic, noisy nature of neural computations. This study introduces the noisy spiking neural network (NSNN) and the noise-driven learning rule (NDL) by incorporating noisy neuronal dynamics to exploit the computational advantages of noisy neural processing. NSNN provides a theoretical framework that yields scalable, flexible, and reliable computation. We demonstrate that NSNN leads to spiking neural models with competitive performance, improved robustness against challenging perturbations than deterministic SNNs, and better reproducing probabilistic computations in neural coding. This study offers a powerful and easy-to-use tool for machine learning, neuromorphic intelligence practitioners, and computational neuroscience researchers.