Stability of the replica symmetric solution in diluted perceptron learning

DOI10.1088/1742-5468/2013/02/L02002MaRDI QIDQ3301481zbMATH OpenWikidataFDO

Authors Alejandro Lage-Castellanos, Andrea Pagnani, Gretel Quintero Angulo

Publication date 11 August 2020

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

Full work available at URL https://arxiv.org/abs/1209.5941

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Dynamic critical phenomena in statistical mechanics (82C27)

Abstract: We study the role played by the dilution in the average behavior of a perceptron model with continuous coupling with the replica method. We analyze the stability of the replica symmetric solution as a function of the dilution field for the generalization and memorization problems. Thanks to a Gardner like stability analysis we show that at any fixed ratio $alpha$ between the number of patterns M and the dimension N of the perceptron ($alpha=M/N$), there exists a critical dilution field $h_c$ above which the replica symmetric ansatz becomes unstable.

Recommendations

• Replica-symmetry breaking in perceptrons
• Learning by dilution in a neural network
• A diluted version of the perceptron model
• Maximal stability in unsupervised learning
• Threshold-induced phase transitions in perceptrons

Cites work

• scientific article; zbMATH DE number 1273988 (Why is no real title available?)
• scientific article; zbMATH DE number 845714 (Why is no real title available?)
• 10.1162/153244303322753616
• Compressed sensing
• Feature extraction. Foundations and applications. Papers from NIPS 2003 workshop on feature extraction, Whistler, BC, Canada, December 11--13, 2003. With CD-ROM.
• Quenched versus annealed dilution in neural networks
• Statistical mechanics of learning
• The space of interactions in neural network models

Cited in

(3)

• Optimal capacity of graded-response perceptrons: a replica-symmetry-breaking solution
• A diluted version of the perceptron model
• Maximal stability in unsupervised learning

This page was built for publication: Stability of the replica symmetric solution in diluted perceptron learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3301481)