SpikePropamine: Differentiable Plasticity in Spiking Neural Networks

TL;DR

This paper introduces a differentiable plasticity framework for spiking neural networks, enabling simultaneous learning of fixed weights and plasticity rules, leading to improved performance on complex temporal and robotic tasks.

Contribution

It presents a novel gradient-based method to learn synaptic plasticity rules in SNNs, enhancing their adaptability and learning capabilities.

Findings

SNNs with differentiable plasticity solve challenging temporal tasks.

The framework learns various plasticity and neuromodulatory rules.

Networks maintain performance in robotic locomotion under novel conditions.

Abstract

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.