Continuous learning of spiking networks trained with local rules

Abstract

Artificial neural networks (ANNs) experience catastrophic forgetting (CF) during sequential learning. In contrast, the brain can learn continuously without any signs of catastrophic forgetting. Spiking neural networks (SNNs) are the next generation of ANNs with many features borrowed from biological neural networks. Thus, SNNs potentially promise better resilience to CF. In this paper, we study the susceptibility of SNNs to CF and test several biologically inspired methods for mitigating catastrophic forgetting. SNNs are trained with biologically plausible local training rules based on spike-timing-dependent plasticity (STDP). Local training prohibits the direct use of CF prevention methods based on gradients of a global loss function. We developed and tested the method to determine the importance of synapses (weights) based on stochastic Langevin dynamics without the need for the gradients. Several other methods of catastrophic forgetting prevention adapted from analog neural networks were tested as well. The experiments were performed on freely available datasets in the SpykeTorch environment.

arXiv comment25 pages

References in corpus (19)

• Overcoming catastrophic forgetting in neural networks
• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• Continual Learning Through Synaptic Intelligence
• STDP-based spiking deep convolutional neural networks for object recognition
• EMNIST: an extension of MNIST to handwritten letters
• On Tiny Episodic Memories in Continual Learning
• Bio-inspired digit recognition using reward-modulated spike-timing-dependent plasticity in deep convolutional networks
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• Episodic Memory in Lifelong Language Learning
• Pseudo-Rehearsal: Achieving Deep Reinforcement Learning without Catastrophic Forgetting
• Neurogenesis Deep Learning
• Selfless Sequential Learning
• Overcoming Long-term Catastrophic Forgetting through Adversarial Neural Pruning and Synaptic Consolidation
• Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks
• Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks
• Few-Shot Self Reminder to Overcome Catastrophic Forgetting
• Using Hindsight to Anchor Past Knowledge in Continual Learning
• Spiking Neural Predictive Coding for Continual Learning from Data Streams

Cited by in corpus (2)

• Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications
• Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems