Replay4NCL: An Efficient Memory Replay-based Methodology for Neuromorphic Continual Learning in Embedded AI Systems

Abstract

Neuromorphic Continual Learning (NCL) paradigm leverages Spiking Neural Networks (SNNs) to enable continual learning (CL) capabilities for AI systems to adapt to dynamically changing environments. Currently, the state-of-the-art employ a memory replay-based method to maintain the old knowledge. However, this technique relies on long timesteps and compression-decompression steps, thereby incurring significant latency and energy overheads, which are not suitable for tightly-constrained embedded AI systems (e.g., mobile agents/robotics). To address this, we propose Replay4NCL, a novel efficient memory replay-based methodology for enabling NCL in embedded AI systems. Specifically, Replay4NCL compresses the latent data (old knowledge), then replays them during the NCL training phase with small timesteps, to minimize the processing latency and energy consumption. To compensate the information loss from reduced spikes, we adjust the neuron threshold potential and learning rate settings. Experimental results on the class-incremental scenario with the Spiking Heidelberg Digits (SHD) dataset show that Replay4NCL can preserve old knowledge with Top-1 accuracy of 90.43% compared to 86.22% from the state-of-the-art, while effectively learning new tasks, achieving 4.88x latency speed-up, 20% latent memory saving, and 36.43% energy saving. These results highlight the potential of our Replay4NCL methodology to further advances NCL capabilities for embedded AI systems.

Accepted at the 62th Design Automation Conference (DAC) 2025, June 2025, San Francisco, CA, USA

References in corpus (16)

• Overcoming catastrophic forgetting in neural networks
• A continual learning survey: Defying forgetting in classification tasks
• Deep Learning in Spiking Neural Networks
• Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networks
• The Heidelberg spiking datasets for the systematic evaluation of spiking neural networks
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• ASP: Learning to Forget with Adaptive Synaptic Plasticity in Spiking Neural Networks
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• Continual Learning and Catastrophic Forgetting
• Controlled Forgetting: Targeted Stimulation and Dopaminergic Plasticity Modulation for Unsupervised Lifelong Learning in Spiking Neural Networks
• 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
• RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
• Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks
• Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks