paper-with-me

Papers

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

2025-03-21 · Mishal Fatima Minhas, Rachmad Vidya Wicaksana Putra, Falah Awwad, Osman Hasan, Muhammad Shafique

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.

📄 PDF Abstract BibTeX arXiv:2503.17061

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

NCL 설명 없음

Similar Papers 제목 키워드 기반

Graph Continual Learning with Debiased Lossless Memory Replay

2024-04-17 · Chaoxi Niu, Guansong Pang, Ling Chen

Real-life graph data often expands continually, rendering the learning of graph neural networks (GNNs) on static graph data impractical. Graph continual learning (GCL) tackles this problem by continually adapting GNNs to…

Continual LearningIncremental Learning

SPICED: A Synaptic Homeostasis-Inspired Framework for Unsupervised Continual EEG Decoding

2025-09-22 · Yangxuan Zhou, Sha Zhao, Jiquan Wang, Haiteng Jiang 외 arxiv

Human brain achieves dynamic stability-plasticity balance through synaptic homeostasis. Inspired by this biological principle, we propose SPICED: a neuromorphic framework that integrates the synaptic homeostasis mechanis…

Continual LearningEeg Decoding

Self-recovery of memory via generative replay

2023-01-15 · Zhenglong Zhou, Geshi Yeung, Anna C. Schapiro

A remarkable capacity of the brain is its ability to autonomously reorganize memories during offline periods. Memory replay, a mechanism hypothesized to underlie biological offline learning, has inspired offline methods …

Continual Learning

Augmenting Replay in World Models for Continual Reinforcement Learning

2024-01-30 · Luke Yang, Levin Kuhlmann, Gideon Kowadlo

Continual RL requires an agent to learn new tasks without forgetting previous ones, while improving on both past and future tasks. The most common approaches use model-free algorithms and replay buffers can help to mitig…

Continual LearningModel-based Reinforcement Learningreinforcement-learningReinforcement Learning+1

Leveraging Complementary Embeddings for Replay Selection in Continual Learning with Small Buffers

2026-04-09 · Danit Yanowsky, Daphna Weinshall arxiv

Catastrophic forgetting remains a key challenge in Continual Learning (CL). In replay-based CL with severe memory constraints, performance critically depends on the sample selection strategy for the replay buffer. Most e…

Continual Learning