Online Continual Learning via Spiking Neural Networks with Sleep Enhanced Latent Replay

• URL: http://arxiv.org/abs/2507.02901v2
• Date: Thu, 10 Jul 2025 02:48:24 GMT
• Title: Online Continual Learning via Spiking Neural Networks with Sleep Enhanced Latent Replay
• Authors: Erliang Lin, Wenbin Luo, Wei Jia, Yu Chen, Shaofu Yang,
• Abstract summary: This paper proposes a novel online continual learning approach termed as SESLR.<n>It incorporates a sleep enhanced latent replay scheme with spiking neural networks (SNNs)<n>Experiments on both conventional (MNIST, CIFAR10) and neuromorphic (NMNIST, CIFAR10-DVS) datasets demonstrate SESLR's effectiveness.
• Score: 8.108335297331658
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Edge computing scenarios necessitate the development of hardware-efficient online continual learning algorithms to be adaptive to dynamic environment. However, existing algorithms always suffer from high memory overhead and bias towards recently trained tasks. To tackle these issues, this paper proposes a novel online continual learning approach termed as SESLR, which incorporates a sleep enhanced latent replay scheme with spiking neural networks (SNNs). SESLR leverages SNNs' binary spike characteristics to store replay features in single bits, significantly reducing memory overhead. Furthermore, inspired by biological sleep-wake cycles, SESLR introduces a noise-enhanced sleep phase where the model exclusively trains on replay samples with controlled noise injection, effectively mitigating classification bias towards new classes. Extensive experiments on both conventional (MNIST, CIFAR10) and neuromorphic (NMNIST, CIFAR10-DVS) datasets demonstrate SESLR's effectiveness. On Split CIFAR10, SESLR achieves nearly 30% improvement in average accuracy with only one-third of the memory consumption compared to baseline methods. On Split CIFAR10-DVS, it improves accuracy by approximately 10% while reducing memory overhead by a factor of 32. These results validate SESLR as a promising solution for online continual learning in resource-constrained edge computing scenarios.

Related papers

• SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network [19.73335869722781]
  Continuous learning of novel classes is crucial for edge devices to preserve data privacy and maintain reliable performance in dynamic environments.<n>In this work, we present an SNN-based method for On-Device FSCIL ie., Sparsity-Aware and Fast Adaptive SNN.
  arXiv  Detail & Related papers  (2025-10-04T03:21:31Z)
• Toward Lifelong Learning in Equilibrium Propagation: Sleep-like and Awake Rehearsal for Enhanced Stability [1.167489362272148]
  We propose a sleep-like replay consolidation (SRC) algorithm for EP-trained RNNs.<n>SRC significantly improves RNN's resilience to catastrophic forgetting in continuous learning scenarios.<n>Our study reveals the applicability of sleep-like replay techniques to RNNs.
  arXiv  Detail & Related papers  (2025-08-12T20:48:02Z)
• A Scalable Hybrid Training Approach for Recurrent Spiking Neural Networks [13.220581846415957]
  In this work, we introduce HYbrid PRopagation (HYPR) that combines the efficiency of parallelization with approximate online forward learning.<n>HYPR enables parallelization of parameter update over the sub sequences for RSNNs consisting of almost arbitrary non-linear spiking neuron models.<n>We find that this type of neuron model is particularly well trainable by HYPR, resulting in an unprecedentedly low task performance gap between approximate forward gradient learning and BPTT.
  arXiv  Detail & Related papers  (2025-06-17T12:27:25Z)
• Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks [45.53312220335389]
  We introduce the first memory-efficient implementation of Latent Replay (LR)-based CL for Spiking Neural Networks (SNNs) LRs combine new samples with latent representations of previously learned data, to mitigate forgetting. Experiments on the Heidelberg SHD dataset with Sample and Class-Incremental tasks reach a Top-1 accuracy of 92.5% and 92%, respectively.
  arXiv  Detail & Related papers  (2024-05-08T09:03:17Z)
• Neuromorphic Online Learning for Spatiotemporal Patterns with a Forward-only Timeline [5.094970748243019]
  Spiking neural networks (SNNs) are bio-plausible computing models with high energy efficiency. Backpropagation Through Time (BPTT) is traditionally used to train SNNs. We present Spatiotemporal Online Learning for Synaptic Adaptation (SOLSA), specifically designed for online learning of SNNs.
  arXiv  Detail & Related papers  (2023-07-21T02:47:03Z)
• Intelligence Processing Units Accelerate Neuromorphic Learning [52.952192990802345]
  Spiking neural networks (SNNs) have achieved orders of magnitude improvement in terms of energy consumption and latency. We present an IPU-optimized release of our custom SNN Python package, snnTorch.
  arXiv  Detail & Related papers  (2022-11-19T15:44:08Z)
• Online Training Through Time for Spiking Neural Networks [66.7744060103562]
  Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. We propose online training through time (OTTT) for SNNs, which is derived from BPTT to enable forward-in-time learning.
  arXiv  Detail & Related papers  (2022-10-09T07:47:56Z)
• Bayesian Neural Network Language Modeling for Speech Recognition [59.681758762712754]
  State-of-the-art neural network language models (NNLMs) represented by long short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming highly complex. In this paper, an overarching full Bayesian learning framework is proposed to account for the underlying uncertainty in LSTM-RNN and Transformer LMs.
  arXiv  Detail & Related papers  (2022-08-28T17:50:19Z)
• DIVISION: Memory Efficient Training via Dual Activation Precision [60.153754740511864]
  State-of-the-art work combines a search of quantization bit-width with the training, which makes the procedure complicated and less transparent. We propose a simple and effective method to compress DNN training. Experiment results show DIVISION has better comprehensive performance than state-of-the-art methods, including over 10x compression of activation maps and competitive training throughput, without loss of model accuracy.
  arXiv  Detail & Related papers  (2022-08-05T03:15:28Z)
• Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learning [54.7584721943286]
  Continual Learning (CL) methods aim to enable machine learning models to learn new tasks without catastrophic forgetting of those that have been previously mastered. Existing CL approaches often keep a buffer of previously-seen samples, perform knowledge distillation, or use regularization techniques towards this goal. We propose to only activate and select sparse neurons for learning current and past tasks at any stage.
  arXiv  Detail & Related papers  (2022-02-21T13:25:03Z)
• Spiking Neural Networks with Improved Inherent Recurrence Dynamics for Sequential Learning [6.417011237981518]
  Spiking neural networks (SNNs) with leaky integrate and fire (LIF) neurons can be operated in an event-driven manner. We show that SNNs can be trained for sequential tasks and propose modifications to a network of LIF neurons. We then develop a training scheme to train the proposed SNNs with improved inherent recurrence dynamics.
  arXiv  Detail & Related papers  (2021-09-04T17:13:28Z)
• Improving Computational Efficiency in Visual Reinforcement Learning via Stored Embeddings [89.63764845984076]
  We present Stored Embeddings for Efficient Reinforcement Learning (SEER) SEER is a simple modification of existing off-policy deep reinforcement learning methods. We show that SEER does not degrade the performance of RLizable agents while significantly saving computation and memory.
  arXiv  Detail & Related papers  (2021-03-04T08:14:10Z)
• Continual Learning in Recurrent Neural Networks [67.05499844830231]
  We evaluate the effectiveness of continual learning methods for processing sequential data with recurrent neural networks (RNNs) We shed light on the particularities that arise when applying weight-importance methods, such as elastic weight consolidation, to RNNs. We show that the performance of weight-importance methods is not directly affected by the length of the processed sequences, but rather by high working memory requirements.
  arXiv  Detail & Related papers  (2020-06-22T10:05:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.