SpikePropamine: Differentiable Plasticity in Spiking Neural Networks

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.

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Playing Atari with Deep Reinforcement Learning
• Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor
• High-Dimensional Continuous Control Using Generalized Advantage Estimation
• STDP-based spiking deep convolutional neural networks for object recognition
• SLAYER: Spike Layer Error Reassignment in Time
• Distributed Distributional Deterministic Policy Gradients
• Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rules
• Towards Biologically Plausible Deep Learning
• Emergence of grid-like representations by training recurrent neural networks to perform spatial localization
• Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
• Supervised Learning in Multilayer Spiking Neural Networks
• Spiking Deep Residual Network
• Unbiasing Truncated Backpropagation Through Time
• Adaptive Reinforcement Learning through Evolving Self-Modifying Neural Networks