NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
A conjugate gradients/trust regions algorithms for training multilayer perceptrons for nonlinear mappingThis paper addresses the issue of applying a globally convergent optimization algorithm to the training of multilayer perceptrons, a class of Artificial Neural Networks. The multilayer perceptrons are trained towards the solution of two highly nonlinear problems: (1) signal detection in a multi-user communication network, and (2) solving the inverse kinematics for a robotic manipulator. The research is motivated by the fact that a multilayer perceptron is theoretically capable of approximating any nonlinear function to within a specified accuracy. The algorithm that has been employed in this study combines the merits of two well known optimization algorithms, the Conjugate Gradients and the Trust Regions Algorithms. The performance is compared to a widely used algorithm, the Backpropagation Algorithm, that is basically a gradient-based algorithm, and hence, slow in converging. The performances of the two algorithms are compared with the convergence rate. Furthermore, in the case of the signal detection problem, performances are also benchmarked by the decision boundaries drawn as well as the probability of error obtained in either case.
Document ID
19930020392
Document Type
Conference Paper
Authors
Madyastha, Raghavendra K. (Rice Univ. Houston, TX, United States)
Aazhang, Behnaam (Rice Univ. Houston, TX, United States)
Henson, Troy F. (International Business Machines Corp. Houston, TX., United States)
Huxhold, Wendy L. (International Business Machines Corp. Houston, TX., United States)
Date Acquired
September 6, 2013
Publication Date
December 1, 1992
Publication Information
Publication: NASA. Johnson Space Center, North American Fuzzy Logic Processing Society (NAFIPS 1992), Volume 2
Subject Category
COMPUTER PROGRAMMING AND SOFTWARE
Distribution Limits
Public
Copyright
Work of the US Gov. Public Use Permitted.

Related Records

IDRelationTitle19930020367Analytic PrimaryNorth American Fuzzy Logic Processing Society (NAFIPS 1992), volume 2