Generalization and learning error for nonlinear perceptron.

DOI10.1016/S0895-7177(01)00163-7MaRDI QIDQ1609463zbMATH OpenFDO

Authors Brunello Tirozzi, M. V. Shcherbina

Publication date 15 August 2002

Published in Mathematical and Computer Modelling (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/S0895-7177(01)00163-7

zbMATH Keywords

law of large numbersperceptronsaddle point

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Psychophysics and psychophysiology; perception (91E30)

Review text

A rigorous derivation of the asymptotic behaviour of learning and prediction error for the nonlinear perceptron is presented. The saddle-point method is used for evaluating these quantities.

Recommendations

• Generalization errors of the simple perceptron
• Learning and generalization errors for the 2D binary perceptron.
• scientific article; zbMATH DE number 1728675
• Generalization in a linear perceptron in the presence of noise
• scientific article; zbMATH DE number 1843046
• scientific article; zbMATH DE number 1453028
• Learning and generalisation. With applications to neural networks.
• Generalization learning in a perceptron with binary synapses
• High-dimensional dynamics of generalization error in neural networks

Cites work

• Generalization errors of the simple perceptron
• On the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
• P-ADIC DYNAMICAL SYSTEMS AND NEURAL NETWORKS

Cited in

(2)

• High-dimensional dynamics of generalization error in neural networks
• Learning and generalization errors for the 2D binary perceptron.

This page was built for publication: Generalization and learning error for nonlinear perceptron.

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1609463)