SpikePropamine: Differentiable Plasticity in Spiking Neural Networks
This work addresses the limitation of static synapses in SNNs for machine learning applications, enabling adaptive learning in noisy and novel environments.
The authors tackled the problem of enabling Spiking Neural Networks (SNNs) to learn synaptic plasticity rules through gradient descent, allowing for adaptive learning beyond initial training. They demonstrated that SNNs with differentiable plasticity solved challenging temporal tasks and achieved near-minimal performance degradation in novel robotic conditions, outperforming traditional SNNs.
The adaptive changes in synaptic efficacy that occur between spiking neurons have been demonstrated to play a critical role in learning for biological neural networks. Despite this source of inspiration, many learning focused applications using Spiking Neural Networks (SNNs) retain static synaptic connections, preventing additional learning after the initial training period. Here, we introduce a framework for simultaneously learning the underlying fixed-weights and the rules governing the dynamics of synaptic plasticity and neuromodulated synaptic plasticity in SNNs through gradient descent. We further demonstrate the capabilities of this framework on a series of challenging benchmarks, learning the parameters of several plasticity rules including BCM, Oja's, and their respective set of neuromodulatory variants. The experimental results display that SNNs augmented with differentiable plasticity are sufficient for solving a set of challenging temporal learning tasks that a traditional SNN fails to solve, even in the presence of significant noise. These networks are also shown to be capable of producing locomotion on a high-dimensional robotic learning task, where near-minimal degradation in performance is observed in the presence of novel conditions not seen during the initial training period.