Rhythmic sharing: A bio-inspired paradigm for zero-shot adaptive learning in neural networks

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Kang, Hoony, Losert, Wolfgang
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866915863480762368
author Kang, Hoony
Losert, Wolfgang
author_facet Kang, Hoony
Losert, Wolfgang
contents The brain rapidly adapts to new contexts and learns from limited data, a coveted characteristic that artificial intelligence (AI) algorithms struggle to mimic. Inspired by the mechanical oscillatory rhythms of neural cells, we developed a learning paradigm utilizing link strength oscillations, where learning is associated with the coordination of these oscillations. Link oscillations can rapidly change coordination, allowing the network to sense and adapt to subtle contextual changes without supervision. The network becomes a generalist AI architecture, capable of predicting dynamics of multiple contexts including unseen ones. These results make our paradigm a powerful starting point for novel models of cognition. Because our paradigm is agnostic to specifics of the neural network, our study opens doors for introducing rapid adaptive learning into leading AI models.
format Preprint
id arxiv_https___arxiv_org_abs_2502_08644
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rhythmic sharing: A bio-inspired paradigm for zero-shot adaptive learning in neural networks
Kang, Hoony
Losert, Wolfgang
Machine Learning
Artificial Intelligence
Dynamical Systems
Adaptation and Self-Organizing Systems
Biological Physics
The brain rapidly adapts to new contexts and learns from limited data, a coveted characteristic that artificial intelligence (AI) algorithms struggle to mimic. Inspired by the mechanical oscillatory rhythms of neural cells, we developed a learning paradigm utilizing link strength oscillations, where learning is associated with the coordination of these oscillations. Link oscillations can rapidly change coordination, allowing the network to sense and adapt to subtle contextual changes without supervision. The network becomes a generalist AI architecture, capable of predicting dynamics of multiple contexts including unseen ones. These results make our paradigm a powerful starting point for novel models of cognition. Because our paradigm is agnostic to specifics of the neural network, our study opens doors for introducing rapid adaptive learning into leading AI models.
title Rhythmic sharing: A bio-inspired paradigm for zero-shot adaptive learning in neural networks
topic Machine Learning
Artificial Intelligence
Dynamical Systems
Adaptation and Self-Organizing Systems
Biological Physics
url https://arxiv.org/abs/2502.08644