Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks

Abstract

Stochastic gradient descent requires that training samples be drawn from a uniformly random distribution of the data. For a deployed system that must learn online from an uncontrolled and unknown environment, the ordering of input samples often fails to meet this criterion, making lifelong learning a difficult challenge. We exploit the locality of the unsupervised Spike Timing Dependent Plasticity (STDP) learning rule to target local representations in a Spiking Neural Network (SNN) to adapt to novel information while protecting essential information in the remainder of the SNN from catastrophic forgetting. In our Controlled Forgetting Networks (CFNs), novel information triggers stimulated firing and heterogeneously modulated plasticity, inspired by biological dopamine signals, to cause rapid and isolated adaptation in the synapses of neurons associated with outlier information. This targeting controls the forgetting process in a way that reduces the degradation of accuracy for older tasks while learning new tasks. Our experimental results on the MNIST dataset validate the capability of CFNs to learn successfully over time from an unknown, changing environment, achieving 95.36% accuracy, which we believe is the best unsupervised accuracy ever achieved by a fixed-size, single-layer SNN on a completely disjoint MNIST dataset.

References in corpus (7)

• Overcoming catastrophic forgetting in neural networks
• PathNet: Evolution Channels Gradient Descent in Super Neural Networks
• Overcoming Catastrophic Forgetting by Incremental Moment Matching
• ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networks
• Continual Learning with Self-Organizing Maps
• Single-Net Continual Learning with Progressive Segmented Training (PST)
• Closed-Loop Memory GAN for Continual Learning

Cited by in corpus (10)

• Securing Deep Spiking Neural Networks against Adversarial Attacks through Inherent Structural Parameters
• Continuous learning of spiking networks trained with local rules
• lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents
• TopSpark: A Timestep Optimization Methodology for Energy-Efficient Spiking Neural Networks on Autonomous Mobile Agents
• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments
• Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks
• Continuous Learning in a Single-Incremental-Task Scenario with Spike Features
• Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems
• L4-Norm Weight Adjustments for Converted Spiking Neural Networks