Machine learning meets physics: A two-way street
This article introduces a special issue on the interaction between the rapidly expanding field
of machine learning and ongoing research in physics. The first half of the papers in this …
of machine learning and ongoing research in physics. The first half of the papers in this …
Statistical mechanics of transfer learning in fully-connected networks in the proportional limit
Transfer learning (TL) is a well-established machine learning technique to boost the
generalization performance on a specific (target) task using information gained from a …
generalization performance on a specific (target) task using information gained from a …
Deep learning-driven predictive tools for damage prediction and optimization in composite hydrogen storage tanks
This research presents a comprehensive framework for predicting the damage in lightweight
composite high-pressure hydrogen storage tanks and optimizes their design to prevent …
composite high-pressure hydrogen storage tanks and optimizes their design to prevent …
[HTML][HTML] Practice Reshapes the Geometry and Dynamics of Task-tailored Representations
A Kikumoto, K Shibata, T Nishio, D Badre - bioRxiv, 2024 - pmc.ncbi.nlm.nih.gov
Extensive practice makes task performance more efficient and precise, leading to
automaticity. However, theories of automaticity differ on which levels of task representations …
automaticity. However, theories of automaticity differ on which levels of task representations …
Transitional probabilities outweigh frequency of occurrence in statistical learning of simultaneously presented visual shapes
AD Endress - Memory & Cognition, 2024 - Springer
Statistical learning is a mechanism for detecting associations among co-occurring elements
in many domains and species. A key controversy is whether it leads to memory for discrete …
in many domains and species. A key controversy is whether it leads to memory for discrete …
Simplified derivations for high-dimensional convex learning problems
DG Clark, H Sompolinsky - arXiv preprint arXiv:2412.01110, 2024 - arxiv.org
Statistical physics provides tools for analyzing high-dimensional problems in machine
learning and theoretical neuroscience. These calculations, particularly those using the …
learning and theoretical neuroscience. These calculations, particularly those using the …
Kernel Shape Renormalization In Bayesian Shallow Networks: a Gaussian Process Perspective
R Pacelli, L Giambagli… - 2024 IEEE Workshop on …, 2024 - ieeexplore.ieee.org
The Bayesian approach has proven to be a valuable tool for analytical inspection of neural
networks. Recent theoretical advances have led to the development of an effective statistical …
networks. Recent theoretical advances have led to the development of an effective statistical …
Delays in generalization match delayed changes in representational geometry
Delayed generalization, also known as``grokking'', has emerged as a well-replicated
phenomenon in overparameterized neural networks. Recent theoretical works associated …
phenomenon in overparameterized neural networks. Recent theoretical works associated …