Issue |
Europhysics News
Volume 56, Number 1, 2025
AI for Physics
|
|
---|---|---|
Page(s) | 13 - 14 | |
Section | Features | |
DOI | https://doi.org/10.1051/epn/2025105 | |
Published online | 24 March 2025 |
Nobel prize in physics 2024: ideas that transcend physics
Departament de Física de la Matèria Condensada and UBICS, Universitat de Barcelona
The Hopfield model, a recurrent artificial neural network introduced in 1982, has had profound implications in computational neuroscience, synchronization phenomena, and artificial intelligence (AI). In computational neuroscience, it provides a framework for understanding associative memory, attractor dynamics, and error correction in biological neural systems. The model’s energy minimization properties have also been explored in synchronization studies, particularly in coupled oscillatory systems and network stability analysis. In AI, Hopfield networks have influenced optimization methods, constraint satisfaction problems, and modern deep learning architectures. This paper reviews the fundamental aspects of the Hopfield model and discusses its lasting impact across these domains.
© European Physical Society, EDP Sciences, 2025
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.