Comment on `The capacity of the Hopfield model'

DOI10.1088/0305-4470/30/22/032zbMATH Open1041.82521arXivcond-mat/9707281OpenAlexW2226944784MaRDI QIDQ4255750

Anton Bovier

Publication date: 5 October 1999

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

Abstract: In a recent paper ``The capacity of the Hopfield model, J. Feng and B. Tirozzi claim to prove rigorous results on the storage capacity that are in conflict with the predictions of the replica approach. We show that their results are in error and that their approach, even when the worst mistakes are corrected, is not giving any mathematically rigorous results.

Full work available at URL: https://arxiv.org/abs/cond-mat/9707281

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)

Recommendations

• Title not available (Why is that?) 👍 👎
• Title not available (Why is that?) 👍 👎
• Title not available (Why is that?) 👍 👎
• Title not available (Why is that?) 👍 👎
• The storage capacity of the Hopfield model and moderate deviations 👍 👎
• Information capacity of the Hopfield model 👍 👎
• The capacity of the Hopfield associative memory 👍 👎
• Capacity of the Hopfield model 👍 👎
• On the storage capacity of the Hopfield model with biased patterns 👍 👎
• On the critical capacity of the Hopfield model. 👍 👎

This page was built for publication: Comment on `The capacity of the Hopfield model'

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4255750)