Matrix momentum for practical natural gradient learning

DOI10.1088/0305-4470/32/22/305zbMath0981.82015OpenAlexW2068774724WikidataQ57660515 ScholiaQ57660515MaRDI QIDQ4950532

Magnus Rattray, Silvia Scarpetta, David Saad

Publication date: 6 April 2000

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

Full work available at URL: https://semanticscholar.org/paper/d7f384384e1186151659f8044e7d0085a62dd370

zbMATH Keywords

neural network learningmatrix momentumon-line learning rule

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Neural nets applied to problems in time-dependent statistical mechanics (82C32)

Related Items (1)

Fast Curvature Matrix-Vector Products for Second-Order Gradient Descent

This page was built for publication: Matrix momentum for practical natural gradient learning