Statistical mechanical analysis of learning dynamics of two-layer perceptron with multiple output units

DOI10.1088/1751-8121/ab0669OpenAlexW2915006549MaRDI QIDQ5053494

Ryo Karakida, Masato Okada, Yuki Yoshida, Shun-ichi Amari

Publication date: 6 December 2022

Published in: Journal of Physics A: Mathematical and Theoretical (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1088/1751-8121/ab0669

zbMATH Keywords

neural networkstatistical mechanicsplateausingular region

Mathematics Subject Classification ID

Quantum theory (81-XX) Statistical mechanics, structure of matter (82-XX)

Related Items (2)

Data-dependence of plateau phenomenon in learning with neural network—statistical mechanical analysis ^* ⋮ An analytic theory of shallow networks dynamics for hinge loss classification*

Cites Work

• Unnamed Item
• On-line learning of a mixture-of-experts neural network
• On-line backpropagation in two-layered neural networks
• Transient dynamics of on-line learning in two-layered neural networks
• Learning by on-line gradient descent
• Dynamics of Learning in MLP: Natural Gradient and Singularity Revisited
• Learning representations by back-propagating errors
• Dynamics of Learning Near Singularities in Layered Networks
• Singularities Affect Dynamics of Learning in Neuromanifolds

This page was built for publication: Statistical mechanical analysis of learning dynamics of two-layer perceptron with multiple output units