A frequency-domain approach to improve ANNs generalization quality via proper initialization

DOI10.1016/J.NEUNET.2018.04.004zbMATH Open1434.68501OpenAlexW2800942579WikidataQ62496295 ScholiaQ62496295MaRDI QIDQ2181069FDOQ2181069

Authors: Majdi Chaari, Afef Fekih, Abdennour C. Seibi, Jalel Ben Hmida 

Publication date: 18 May 2020

Published in: Neural Networks (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.neunet.2018.04.004

Recommendations

• Structural, Syntactic, and Statistical Pattern Recognition
• A Neighborhood-Based Enhancement of the Gauss-Newton Bayesian Regularization Training Method
• scientific article; zbMATH DE number 1928643
• Improving generalization of MLPs with multi-objective optimization
• Research on generalization capability of feedforward neural networks

zbMATH Keywords

artificial intelligencefrequency response functionnetwork initializationmultilayered perceptronnetwork generalization

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Cites Work

• Title not available (Why is that?)
• Why does unsupervised pre-training help deep learning?
• Title not available (Why is that?)
• Generalized frequency response function matrix for MIMO non-linear systems
• Recursive algorithm for computing the frequency response of a class of non-linear difference equation models
• Title not available (Why is that?)
• Analytical Foundations of Volterra Series
• Title not available (Why is that?)
• Frequency response functions for nonlinear rational models
• Sufficiency of excitation
• Title not available (Why is that?)
• Solving the linear interval tolerance problem for weight initialization of neural networks

This page was built for publication: A frequency-domain approach to improve ANNs generalization quality via proper initialization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2181069)