On the optimal weight of a perceptron with Gaussian data and arbitrary nonlinearity

Loading...
Thumbnail Image
Authors
Feuer, Arie
Cristi, Roberto
Subjects
Advisors
Date of Issue
1993-06
Date
Publisher
IEEE
Language
Abstract
In this correspondence we investigate the solution to the following problem: Find the optimal weighted sum of given signals when the optimality criteria is the expected value of a function of this sum and a given "training" signal. The optimality criteria can be a nonlin­ear function from a very large family of possible functions. A number of interesting cases fall under this general framework, such as a single layer perceptron with any of the commonly used nonlinearities, the LMS, the LMF or higher moments, or the various sign algorithms. Assuming the signals to be jointly Gaussian we show that the optimal solution, when it exits, is always collinear with the well-known Wiener solution, and only its scaling factor depends on the particular functions chosen. We also present necessary constructive conditions for the existance of the optimal solution.
Type
Article
Description
Series/Report No
Department
Electrical and Computer Engineering
Organization
Naval Postgraduate School (U.S.)
Identifiers
NPS Report Number
Sponsors
Funder
Format
3 p.
Citation
A. Feuer, R. Cristi, "On the optimal weight of a perceptron with Gaussian data and arbitrary nonlinearity," IEEE Transactions on Signal Processing, v.41, no.6, (June 1993), pp. 2257-2259
Distribution Statement
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.
Collections