paper-with-me

홈 › Papers

Mistake gating leads to energy and memory efficient continual learning

2026-04-15 · Aaron Pache, Mark CW van Rossum arxiv

Synaptic plasticity is metabolically expensive, yet animals continuously update their internal models without exhausting energy reserves. However, when artificial neural networks are trained, the network parameters are typically updated on every sample that is presented, even if the sample was classified correctly. Inspired by the human negativity bias and error-related negativity, we propose 'memorized mistake-gated learning' -- a biologically plausible plasticity rule where synaptic updates are strictly gated by current and past classification errors. This reduces the number of updates the network needs to make by $50\%\sim80\%$. Mistake gating is particularly well suited in two cases: 1) For incremental learning where new knowledge is acquired on a background of pre-existing knowledge, 2) For online learning scenarios when data needs to be stored for later replay, as mistake-gating reduces storage buffer requirements. The algorithm can be implemented in a few lines of code, adds no hyper-parameters, and comes at negligible computational overhead. Learning on mistakes is an energy efficient and biologically relevant modification to commonly used learning rules that is well suited for continual learning.

📄 PDF Abstract BibTeX arXiv:2604.14336

Code (0)

등록된 구현이 없습니다.

Tasks

Incremental LearningContinual Learning

Similar Papers 제목 키워드 기반

Continual Learning with Neuromorphic Computing: Theories, Methods, and Applications

2024-10-11 · Mishal Fatima Minhas, Rachmad Vidya Wicaksana Putra, Falah Awwad, Osman Hasan 외

To adapt to real-world dynamics, intelligent systems need to assimilate new knowledge without catastrophic forgetting, where learning new tasks leads to a degradation in performance on old tasks. To address this, continu…

Continual Learning

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

2022-11-17 · CVPR 2023 1 · James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle, Donghyun Kim 외

Recently, large-scale pre-trained Vision-and-Language (VL) foundation models have demonstrated remarkable capabilities in many zero-shot downstream tasks, achieving competitive results for recognizing objects defined by …

Memory-Statistics Tradeoff in Continual Learning with Structural Regularization

2025-04-05 · Haoran Li, Jingfeng Wu, Vladimir Braverman

We study the statistical performance of a continual learning problem with two linear regression tasks in a well-specified random design setting. We consider a structural regularization algorithm that incorporates a gener…

Continual Learning

An Attention-based Feature Memory Design for Energy-Efficient Continual Learning

2025-10-06 · Yuandou Wang, Filip Gunnarsson, Rihan Hai arxiv

Tabular data streams are increasingly prevalent in real-time decision-making across healthcare, finance, and the Internet of Things, often generated and processed on resource-constrained edge and mobile devices. Continua…

Continual Learning

Probabilistic Metaplasticity for Continual Learning with Memristors

2024-03-13 · Fatima Tuz Zohora, Vedant Karia, Nicholas Soures, Dhireesha Kudithipudi

Edge devices operating in dynamic environments critically need the ability to continually learn without catastrophic forgetting. The strict resource constraints in these devices pose a major challenge to achieve this, as…

Continual Learning