Comprehensibility maximization and humanly comprehensible representations

DOI10.1080/03081079.2011.643471zbMath1274.93003OpenAlexW2148132233MaRDI QIDQ2862325

Ryotaro Kamimura

Publication date: 14 November 2013

Published in: International Journal of General Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/03081079.2011.643471

zbMATH Keywords

neural networksmutual informationcompetitive learninginformation-theoreticSOM

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) General systems (93A10) Measures of information, entropy (94A17)

Uses Software

• SOM

Cites Work

• Generating rules with predicates, terms and variables from the pruned neural networks
• V4 receptive field dynamics as predicted by a systems-level model of visual attention using feedback from the frontal eye field
• Attention in natural scenes: neurophysiological and computational bases
• Attention as a controller
• Advanced visualization of self-organizing maps with vector fields
• Vector quantization using information theoretic concepts
• SOM-based data visualization methods
• A Penalty-Function Approach for Pruning Feedforward Neural Networks
• 10.1162/153244303322753616
• 10.1162/153244303322753742
• Learning from examples with information theoretic criteria
• Symbolic knowledge extraction from trained neural networks: A sound approach
• Rule extraction from expert heuristics: A comparative study of rough sets with neural networks and ID3

This page was built for publication: Comprehensibility maximization and humanly comprehensible representations