Rough Neural Computing: Techniques for Computing with Words

Citation

Rigelsford, J. (2004), "Rough Neural Computing: Techniques for Computing with Words", Industrial Robot, Vol. 31 No. 6, pp. 534-534. https://doi.org/10.1108/ir.2004.31.6.534.1

This book is part of the Cognitive Technologies series, which addresses key areas of artificial intelligence including cognitive robotics, artificial life, the semantic web, and intelligent tutoring systems. “Rough Neural Computing” explores computing based on information granulation and covers neural networks, rough sets, and rough‐fuzzy hybridisation.

The first part of the book provides fundamental concepts relating to rough sets, granular computing, and rough‐neural computing. It contains seven chapters including “Information Granules and Rough‐Neural Computing”, “Knowledge‐Based Networking in Granular Worlds”, and “Adaptive Aspects of Combining Approximation Spaces”.

Part II, Hybrid Approaches, presents topics including “Approximation Transducers and Trees: A Technique for Combining Rough and Crisp Knowledge”, “On Model Evaluation, Indexes of Importance, and Interaction Values in Rough Set Analysis”, New Fuzzy Rough Sets Based on Certainty Qualification” and “Rough‐SOM with Fuzzy Discretization”.

“Biomedical Inference: A Semantic Model”, “Fundamental Mathematical Notions of the Theory of Socially Embedded Games: A Granular Computing Perspective”, “Rough Neurons: Petri Net Models and Applications” and “Information Granulation in a Decision‐Theoretical Model of Rough Sets”, are amongst the topics discussed in part three, Exemplary Application Areas. The final part of the book comprises nine case studies, which include “Intelligent Acquisition of Audio Signals Employing Neural Networks and Rough Set Algorithms”, “Rough‐Neural Approach to Testing the Influence of Visual Cues on Surround Sound Perception”, “Information Granulation and Pattern Recognition”, “Computational Analysis of Acquired Dyslexia of Kanji Characters Based on Conventional and Rough Neural Networks” and “A Hybrid Model for Rule Discovery in Data”.

“Rough Neural Computing” provides the background information and application‐based examples that make the book suitable for advanced postgraduate students, while the extended theoretical sections make it useful for academic researchers and professional specialists.