Exact learning dynamics of deep linear networks with prior knowledge

DOI10.1088/1742-5468/AD01B8MaRDI QIDQ6539417zbMATH OpenFDO

Authors Clémentine C. J. Dominé, Lukas Braun, James E. Fitzgerald, Andrew M. Saxe

Publication date 14 May 2024

Published in Journal of Cosmology and Astroparticle Physics (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://doi.org/10.1088/1742-5468/AD01B8

zbMATH Keywords

deep learninglearning theorymachine learning

Mathematics Subject Classification ID

Relativity and gravitational theory (83-XX)

Cites work

• A mathematical theory of semantic development in deep neural networks
• A mean field view of the landscape of two-layer neural networks
• Learning by on-line gradient descent
• Mean field analysis of neural networks: a central limit theorem
• Overcoming catastrophic forgetting in neural networks
• Transfer learning for reinforcement learning domains: a survey

This page was built for publication: Exact learning dynamics of deep linear networks with prior knowledge

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6539417)