Bruck, Jehoshua (1989) Harmonic analysis of neural networks. In: Twenty-Third Asilomar Conference on Signals, Systems and Computers. Maple Press , San Jose, CA, pp. 142-146. ISBN 0-929029-30-1 http://resolver.caltech.edu/CaltechAUTHORS:20120524-090912809
- Published Version
See Usage Policy.
Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20120524-090912809
Neural networks models have attracted a lot of interest in recent years mainly because there were perceived as a new idea for computing. These models can be described as a network in which every node computes a linear threshold function. One of the main difficulties in analyzing the properties of these networks is the fact that they consist of nonlinear elements. I will present a novel approach, based on harmonic analysis of Boolean functions, to analyze neural networks. In particular I will show how this technique can be applied to answer the following two fundamental questions (i) what is the computational power of a polynomial threshold element with respect to linear threshold elements? (ii) Is it possible to get exponentially many spurious memories when we use the outer-product method for programming the Hopfield model?
|Item Type:||Book Section|
|Additional Information:||© 1989 Maple Press. Date of Current Version: 28 May 2003.|
|Official Citation:||Bruck, J.; , "Harmonic analysis of neural networks," Signals, Systems and Computers, 1989. Twenty-Third Asilomar Conference on , vol.1, no., pp. 142- 146, 1989 doi: 10.1109/ACSSC.1989.1200767 URL: http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1200767&isnumber=27032|
|Usage Policy:||No commercial reproduction, distribution, display or performance rights in this work are provided.|
|Deposited By:||Tony Diaz|
|Deposited On:||06 Jun 2012 17:57|
|Last Modified:||26 Dec 2012 15:15|
Repository Staff Only: item control page