Wang L., Fu X. Data Mining with Computational Intelligence

Springer, 2005. — 276 p. — (Advanced Information and Knowledge Processing). — ISBN 978-3-540-24522-3.This book systematically presents how to utilize fuzzy neural networks, multi-layer perceptron (MLP) neural networks, radial basis function (RBF)
neural networks, genetic algorithms (GAs), and support vector machines (SVMs) in data mining tasks. Fuzzy logic mimics the imprecise way of reasoning in natural languages and is capable of tolerating uncertainty and vagueness. The MLP is perhaps the most popular type of neural network used today. The RBF neural network has been attracting great interest because of its locally tuned response in RBF neurons like biological neurons and its global approximation capability. This book demonstrates the power of GAs in feature selection and rule extraction. SVMs are well known for their excellent accuracy and generalization abilities.MLP Neural Networks for Time-Series Prediction and Classification
Fuzzy Neural Networks for Bioinformatics
An Improved RBF Neural Network Classifier
Attribute Importance Ranking for Data Dimensionality Reduction
Genetic Algorithms for Class-Dependent Feature Selection
Rule Extraction from RBF Neural Networks
A Hybrid Neural Network For Protein Secondary Structure Prediction
Support Vector Machines for Prediction
Rule Extraction from Support Vector Machines
Appendix. Rules extracted for the Iris data set