Continual Learning with Neuromorphic Computing: Foundations, Methods, and Emerging Applications

Abstract

The challenging deployment of compute- and memory-intensive methods from Deep Neural Network (DNN)-based Continual Learning (CL) underscores the critical need for a paradigm shift towards more efficient approaches. Neuromorphic Continual Learning (NCL) appears as an emerging solution, by leveraging the principles of Spiking Neural Networks (SNNs) which enable efficient CL algorithms executed in dynamically-changed environments with resource-constrained computing systems. Motivated by the need for a holistic study of NCL, in this survey, we first provide a detailed background on CL, encompassing the desiderata, settings, metrics, scenario taxonomy, Online Continual Learning (OCL) paradigm, recent DNN-based methods to address catastrophic forgetting (CF). Then, we analyze these methods considering CL desiderata, computational and memory costs, as well as network complexity, hence emphasizing the need for energy-efficient CL. Afterward, we provide background of low-power neuromorphic systems including encoding techniques, neuronal dynamics, network architectures, learning rules, hardware processors, software and hardware frameworks, datasets, benchmarks, and evaluation metrics. Then, this survey comprehensively reviews and analyzes state-of-the-art in NCL. The key ideas, implementation frameworks, and performance assessments are also provided. This survey covers several hybrid approaches that combine supervised and unsupervised learning paradigms. It also covers optimization techniques including SNN operations reduction, weight quantization, and knowledge distillation. Then, this survey discusses the progress of real-world NCL applications. Finally, this paper provides a future perspective on the open research challenges for NCL, since the purpose of this study is to be useful for the wider neuromorphic AI research community and to inspire future research in bio-plausible OCL.

This work has been accepted for publication in IEEE Access

References in corpus (29)

• Three scenarios for continual learning
• Class-Incremental Learning: A Survey
• MorphIC: A 65-nm 738k-Synapse/mm${}^2$ Quad-Core Binary-Weight Digital Neuromorphic Processor with Stochastic Spike-Driven Online Learning
• ReckOn: A 28nm Sub-mm2 Task-Agnostic Spiking Recurrent Neural Network Processor Enabling On-Chip Learning over Second-Long Timescales
• SpykeTorch: Efficient Simulation of Convolutional Spiking Neural Networks with at most one Spike per Neuron
• PyCIL: A Python Toolbox for Class-Incremental Learning
• Incorporating Neuro-Inspired Adaptability for Continual Learning in Artificial Intelligence
• BrainCog: A Spiking Neural Network based Brain-inspired Cognitive Intelligence Engine for Brain-inspired AI and Brain Simulation
• FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks
• Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments
• Continual Learning and Catastrophic Forgetting
• ReSpawn: Energy-Efficient Fault-Tolerance for Spiking Neural Networks considering Unreliable Memories
• Continual SLAM: Beyond Lifelong Simultaneous Localization and Mapping Through Continual Learning
• ES-ImageNet: A Million Event-Stream Classification Dataset for Spiking Neural Networks
• SoftSNN: Low-Cost Fault Tolerance for Spiking Neural Network Accelerators under Soft Errors
• EnforceSNN: Enabling Resilient and Energy-Efficient Spiking Neural Network Inference considering Approximate DRAMs for Embedded Systems
• Embodied Neuromorphic Artificial Intelligence for Robotics: Perspectives, Challenges, and Research Development Stack
• Continuous learning of spiking networks trained with local rules
• SNN4Agents: A Framework for Developing Energy-Efficient Embodied Spiking Neural Networks for Autonomous Agents
• N-Omniglot, a large-scale neuromorphic dataset for spatio-temporal sparse few-shot learning
• lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents
• RescueSNN: Enabling Reliable Executions on Spiking Neural Network Accelerators under Permanent Faults
• SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems
• Continual Learning with Guarantees via Weight Interval Constraints
• Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks
• SpiKernel: A Kernel Size Exploration Methodology for Improving Accuracy of the Embedded Spiking Neural Network Systems
• FastSpiker: Enabling Fast Training for Spiking Neural Networks on Event-based Data through Learning Rate Enhancements for Autonomous Embedded Systems
• A Methodology to Study the Impact of Spiking Neural Network Parameters considering Event-Based Automotive Data
• Operationalizing AI in Future Networks: A Bird's Eye View from the System Perspective

Cited by in corpus (2)

• SpikeNAS: A Fast Memory-Aware Neural Architecture Search Framework for Spiking Neural Network-based Embedded AI Systems
• Enabling Efficient Processing of Spiking Neural Networks with On-Chip Learning on Commodity Neuromorphic Processors for Edge AI Systems