Generating rules with predicates, terms and variables from the pruned neural networks

DOI10.1016/J.NEUNET.2009.02.001zbMATH Open1335.68207DBLPjournals/nn/Nayak09OpenAlexW1995604850WikidataQ51849251 ScholiaQ51849251MaRDI QIDQ280332FDOQ280332

Authors: Richi Nayak 

Publication date: 10 May 2016

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

Full work available at URL: https://eprints.qut.edu.au/30070/1/c30070.pdf

Recommendations

• scientific article; zbMATH DE number 2087697
• Rule extraction from trained neural networks using genetic algorithms
• Symbolic knowledge extraction from trained neural networks governed by Łukasiewicz logics
• Symbolic knowledge extraction from trained neural networks: A sound approach
• scientific article; zbMATH DE number 2044650

zbMATH Keywords

pruningfirst-order rulespropositional rulesrule extraction

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Knowledge representation (68T30)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Generalized subsumption and its applications to induction and redundancy
• Is it worth generating rules from neural network ensembles?
• A Penalty-Function Approach for Pruning Feedforward Neural Networks
• Extracting Rules from Neural Networks by Pruning and Hidden-Unit Splitting
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Title not available (Why is that?)
• Neural network explanation using inversion

Cited In (2)

• Title not available (Why is that?)
• Comprehensibility maximization and humanly comprehensible representations

This page was built for publication: Generating rules with predicates, terms and variables from the pruned neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q280332)