Disentangling feature and lazy training in deep neural networks

DOI10.1088/1742-5468/abc4dezbMath1459.68184arXiv1906.08034OpenAlexW3108365919MaRDI QIDQ5857444

A. Jacot, Mario Geiger, Stefano Spigler, Matthieu Wyart

Publication date: 1 April 2021

Published in: Journal of Statistical Mechanics: Theory and Experiment (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1906.08034

zbMATH Keywords

machine learningdeep learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (7)

Relative stability toward diffeomorphisms indicates performance in deep nets* ⋮ Unnamed Item ⋮ Harmonic analysis of network systems via kernels and their boundary realizations ⋮ Landscape and training regimes in deep learning ⋮ Linearized two-layers neural networks in high dimension ⋮ Geometric compression of invariant manifolds in neural networks ⋮ An analytic theory of shallow networks dynamics for hinge loss classification*

Uses Software

• Adam
• Fashion-MNIST

Cites Work

• Bayesian learning for neural networks

This page was built for publication: Disentangling feature and lazy training in deep neural networks