Learning Algorithms for Neural Networks Based on Quasi-Newton Methods With Self-Scaling

[+] Author and Article Information
H. S. M. Beigi, C. J. Li

Department of Mechanical Engineering, Columbia University, New York, NY 10027

J. Dyn. Sys., Meas., Control 115(1), 38-43 (Mar 01, 1993) (6 pages) doi:10.1115/1.2897405 History: Received July 16, 1990; Revised June 01, 1992; Online March 17, 2008


Previous studies have suggested that, for moderate sized neural networks, the use of classical Quasi-Newton methods yields the best convergence properties among all the state-of-the-art [1]. This paper describes a set of even better learning algorithms based on a class of Quasi-Newton optimization techniques called Self-Scaling Variable Metric (SSVM) methods. One of the characteristics of SSVM methods is that they provide a set of search directions which are invariant under the scaling of the objective function. With an XOR benchmark and an encoder benchmark, simulations using the SSVM algorithms for the learning of general feedforward neural networks were carried out to study their performance. Compared to classical Quasi-Newton methods, it is shown that the SSVM method reduces the number of iterations required for convergence by 40 percent to 60 percent that of the classical Quasi-Newton methods which, in general, converge two to three orders of magnitude faster than the steepest descent techniques.

Copyright © 1993 by The American Society of Mechanical Engineers
Your Session has timed out. Please sign back in to continue.





Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In