learning algorithms

2 items

RESEARCHarXiv CS.AI·4/17/2026

Mistake gating leads to energy and memory efficient continual learning

This paper proposes 'memorized mistake-gated learning,' a biologically plausible plasticity rule where synaptic updates are strictly gated by current and past classification errors. This method reduces network updates by 50-80%, significantly enhancing energy and memory efficiency in continual and online learning scenarios.

neural networks efficiency learning algorithms Continual Learning

RESEARCHarXiv CS.LG·4/9/2026

Spectral Edge Dynamics Reveal Functional Modes of Learning

This research explores how spectral edge dynamics can reveal the functional modes through which learning occurs. It delves into the underlying mechanisms of learning processes.

neural networks computational neuroscience machine learning learning algorithms