Feature Extraction

1. Front Matter

   Pages I-XXIV

   PDF

2. An Introduction to Feature Extraction

   1. An Introduction to Feature Extraction

      • Isabelle Guyon, André Elisseeff

      Pages 1-25

3. Feature Extraction Fundamentals

   1. Front Matter

      Pages 27-27

      PDF

   2. Learning Machines

      • Norbert Jankowski, Krzysztof Grabczewski

      Pages 29-64

   3. Assessment Methods

      • Gérard Dreyfus, Isabelle Guyon

      Pages 65-88

   4. Filter Methods

      • Włodzisław Duch

      Pages 89-117

   5. Search Strategies

      • Juha Reunanen

      Pages 119-136

   6. Embedded Methods

      • Thomas Navin Lal, Olivier Chapelle, Jason Weston, André Elisseeff

      Pages 137-165

   7. Information-Theoretic Methods

      • Kari Torkkola

      Pages 167-185

   8. Ensemble Learning

      • Eugene Tuv

      Pages 187-204

   9. Fuzzy Neural Networks

      • Madan M. Gupta, Noriyasu Homma, Zeng-Guang Hou

      Pages 205-233

4. Feature Selection Challenge

   1. Front Matter

      Pages 235-235

      PDF

   2. Design and Analysis of the NIPS2003 Challenge

      • Isabelle Guyon, Steve Gunn, Asa Ben Hur, Gideon Dror

      Pages 237-263

   3. High Dimensional Classification with Bayesian Neural Networks and Dirichlet Diffusion Trees

      • Radford M. Neal, Jianguo Zhang

      Pages 265-296

   4. Ensembles of Regularized Least Squares Classifiers for High-Dimensional Problems

      • Kari Torkkola, Eugene Tuv

      Pages 297-313

   5. Combining SVMs with Various Feature Selection Strategies

      • Yi-Wei Chen, Chih-Jen Lin

      Pages 315-324

   6. Feature Selection with Transductive Support Vector Machines

      • Zhili Wu, Chunhung Li

      Pages 325-341

   7. Variable Selection using Correlation and Single Variable Classifier Methods: Applications

      • Amir Reza Saffari Azar Alamdari

      Pages 343-358

   8. Tree-Based Ensembles with Dynamic Soft Feature Selection

      • Alexander Borisov, Victor Eruhimov, Eugene Tuv

      Pages 359-374

   9. Sparse, Flexible and Efficient Modeling using L ₁ Regularization

      • Saharon Rosset, Ji Zhu

      Pages 375-394

Everyonelovesagoodcompetition. AsIwritethis,twobillionfansareeagerly anticipating the 2006 World Cup. Meanwhile, a fan base that is somewhat smaller (but presumably includes you, dear reader) is equally eager to read all about the results of the NIPS 2003 Feature Selection Challenge, contained herein. Fans of Radford Neal and Jianguo Zhang (or of Bayesian neural n- works and Dirichlet di?usion trees) are gloating “I told you so” and looking forproofthattheirwinwasnota?uke. Butthematterisbynomeanssettled, and fans of SVMs are shouting “wait ’til next year!” You know this book is a bit more edgy than your standard academic treatise as soon as you see the dedication: “To our friends and foes. ” Competition breeds improvement. Fifty years ago, the champion in 100m butter?yswimmingwas22percentslowerthantoday’schampion;thewomen’s marathon champion from just 30 years ago was 26 percent slower. Who knows how much better our machine learning algorithms would be today if Turing in 1950 had proposed an e?ective competition rather than his elusive Test? But what makes an e?ective competition? The ?eld of Speech Recognition hashadNIST-runcompetitionssince1988;errorrateshavebeenreducedbya factorofthreeormore,butthe?eldhasnotyethadtheimpactexpectedofit. Information Retrieval has had its TREC competition since 1992; progress has been steady and refugees from the competition have played important roles in the hundred-billion-dollar search industry. Robotics has had the DARPA Grand Challenge for only two years, but in that time we have seen the results go from complete failure to resounding success (although it may have helped that the second year’s course was somewhat easier than the ?rst’s).

• Feature Extraction
• Feature Selection
• Fuzzy
• Machine Learning
• Statistical Learning
• algorithm
• algorithms
• calculus
• cognition
• learning
• learning theory
• linear optimization
• modeling
• sets
• speech recognition

• Clopinet, Berkeley, USA

  Isabelle Guyon

• Department of Electrical Engineering & Computer Science — EECS, University of California, Berkeley, USA

  Masoud Nikravesh

• School of Electronics and Computer Sciences, University of Southampton, Southampton Highfield, UK

  Steve Gunn

• Division of Computer Science Lab. Electronics Research, University of California, Berkeley, USA

  Lotfi A. Zadeh

Policies and ethics