Kernel Based Algorithms for Mining Huge Data Sets: Supervised, Semi-supervised, and Unsupervised Learning

Bozena Kostek9783540257295, 3-540-25729-2

“Kernel Based Algorithms for Mining Huge Data Sets” is the first book treating the fields of supervised, semi-supervised and unsupervised machine learning collectively. The book presents both the theory and the algorithms for mining huge data sets by using support vector machines (SVMs) in an iterative way. It demonstrates how kernel based SVMs can be used for dimensionality reduction (feature elimination) and shows the similarities and differences between the two most popular unsupervised techniques, the principal component analysis (PCA) and the independent component analysis (ICA). The book presents various examples, software, algorithmic solutions enabling the reader to develop their own codes for solving the problems. The book is accompanied by a website for downloading both data and software for huge data sets modeling in a supervised and semisupervised manner, as well as MATLAB based PCA and ICA routines for unsupervised learning. The book focuses on a broad range of machine learning algorithms and it is particularly aimed at students, scientists, and practicing researchers in bioinformatics (gene microarrays), text-categorization, numerals recognition, as well as in the images and audio signals de-mixing (blind source separation) areas.

---

Table of contents :
Kernel Based Algorithms for Mining Huge Data Sets……Page 1
Preface……Page 8
Contents……Page 13
1 Introduction……Page 17
2 Support Vector Machines in Classification and Regression – An Introduction……Page 26
3 Iterative Single Data Algorithm for Kernel Machines from Huge Data Sets: Theory and Performance……Page 76
4 Feature Reduction with Support Vector Machines and Application in DNA Microarray Analysis……Page 111
5 Semi-supervised Learning and Applications……Page 138
6 Unsupervised Learning by Principal and Independent Component Analysis……Page 187
A Support Vector Machines……Page 221
B Matlab Code for ISDA Classification……Page 228
C Matlab Code for ISDA Regression……Page 233
D Matlab Code for Conjugate Gradient Method with Box Constraints……Page 239
E Uncorrelatedness and Independence……Page 242
F Independent Component Analysis by Empirical Estimation of Score Functions i.e., Probability Density Functions……Page 246
G SemiL User Guide……Page 250
References……Page 255
Index……Page 264