Find out how to access previewonly content
Theoretical Advances in Neural Computation and Learning
pp 391424
Learning Boolean Functions via the Fourier Transform
 Yishay MansourAffiliated withComputer Science Department, Tel Aviv University
Abstract
The importance of using the “right” representation of a function in order to “approximate” it has been widely recognized. The Fourier Transform representation of a function is a classic representation which is widely used to approximate real functions (i.e. functions whose inputs are real numbers). However, the Fourier Transform representation for functions whose inputs are boolean has been far less studied. On the other hand it seems that the Fourier Transform representation can be used to learn many classes of boolean functions.
 Title
 Learning Boolean Functions via the Fourier Transform
 Book Title
 Theoretical Advances in Neural Computation and Learning
 Book Part
 Part II
 Pages
 pp 391424
 Copyright
 1994
 DOI
 10.1007/9781461526964_11
 Print ISBN
 9781461361602
 Online ISBN
 9781461526964
 Publisher
 Springer US
 Copyright Holder
 Springer Science+Business Media New York
 Additional Links
 Topics
 Industry Sectors
 eBook Packages
 Editors

 Vwani Roychowdhury ^{(1)}
 KaiYeung Siu ^{(2)}
 Alon Orlitsky ^{(3)}
 Editor Affiliations

 1. Purdue University
 2. University of California
 3. AT&T Bell Laboratories
 Authors

 Yishay Mansour ^{(4)}
 Author Affiliations

 4. Computer Science Department, Tel Aviv University, Tel Aviv, Israel
Continue reading...
To view the rest of this content please follow the download PDF link above.