paper-with-me

Papers

Compressed Latent Replays for Lightweight Continual Learning on Spiking Neural Networks

2024-05-08 · Alberto Dequino, Alessio Carpegna, Davide Nadalini, Alessandro Savino, Luca Benini, Stefano Di Carlo, Francesco Conti

Rehearsal-based Continual Learning (CL) has been intensely investigated in Deep Neural Networks (DNNs). However, its application in Spiking Neural Networks (SNNs) has not been explored in depth. In this paper we introduce the first memory-efficient implementation of Latent Replay (LR)-based CL for SNNs, designed to seamlessly integrate with resource-constrained devices. 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, without forgetting the previously learned information. Furthermore, we minimize the LRs' requirements by applying a time-domain compression, reducing by two orders of magnitude their memory requirement, with respect to a naive rehearsal setup, with a maximum accuracy drop of 4%. On a Multi-Class-Incremental task, our SNN learns 10 new classes from an initial set of 10, reaching a Top-1 accuracy of 78.4% on the full test set.

📄 PDF Abstract BibTeX arXiv:2407.03111

Code (1)

dequino/spiking-compressed-continual-learning 공식 구현 pytorch

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

SET Dynamic Sparse Training method where weight mask is updated randomly periodically
SNN Spiking Neural Networks (SNNs) are a class of artificial neural networks inspired by the structure and functioning of the brain's neural networks. Unlike traditional…

Similar Papers 제목 키워드 기반

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 외

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…

Continual Learning

A TinyML Platform for On-Device Continual Learning with Quantized Latent Replays

2021-10-20 · Leonardo Ravaglia, Manuele Rusci, Davide Nadalini, Alessandro Capotondi 외

In the last few years, research and development on Deep Learning models and techniques for ultra-low-power devices in a word, TinyML has mainly focused on a train-then-deploy assumption, with static models that cannot be…

Continual LearningQuantization

Integrating Curricula with Replays: Its Effects on Continual Learning

2023-07-08 · Ren Jie Tee, Mengmi Zhang

Humans engage in learning and reviewing processes with curricula when acquiring new skills or knowledge. This human learning behavior has inspired the integration of curricula with replay methods in continual learning ag…

Continual LearningTransfer Learning

Stable-Drift: A Patient-Aware Latent Drift Replay Method for Stabilizing Representations in Continual Learning

2025-11-27 · Paraskevi-Antonia Theofilou, Anuhya Thota, Stefanos Kollias, Mamatha Thota arxiv

When deep learning models are sequentially trained on new data, they tend to abruptly lose performance on previously learned tasks, a critical failure known as catastrophic forgetting. This challenge severely limits the …

Continual LearningDomain Adaptation

Variational Prototype Replays for Continual Learning

2019-05-23 · Mengmi Zhang, Tao Wang, Joo Hwee Lim, Gabriel Kreiman 외

Continual learning refers to the ability to acquire and transfer knowledge without catastrophically forgetting what was previously learned. In this work, we consider \emph{few-shot} continual learning in classification t…

Continual LearningGeneral ClassificationMetric LearningNovel Concepts