Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

Recursive least-squares learning algorithms for neural networks

Conference ·
OSTI ID:6698032
 [1];  [2]
  1. Los Alamos National Lab., NM (USA)
  2. Washington Univ., Seattle, WA (USA). Dept. of Electrical Engineering

This paper presents the development of a pair of recursive least squares (RLS) algorithms for online training of multilayer perceptrons, which are a class of feedforward artificial neural networks. These algorithms incorporate second order information about the training error surface in order to achieve faster learning rates than are possible using first order gradient descent algorithms such as the generalized delta rule. A least squares formulation is derived from a linearization of the training error function. Individual training pattern errors are linearized about the network parameters that were in effect when the pattern was presented. This permits the recursive solution of the least squares approximation, either via conventional RLS recursions or by recursive QR decomposition-based techniques. The computational complexity of the update is in the order of (N{sup 2}), where N is the number of network parameters. This is due to the estimation of the N {times} N inverse Hessian matrix. Less computationally intensive approximations of the RLS algorithms can be easily derived by using only block diagonal elements of this matrix, thereby partitioning the learning into independent sets. A simulation example is presented in which a neural network is trained to approximate a two dimensional Gaussian bump. In this example, RLS training required an order of magnitude fewer iterations on average (527) than did training with the generalized delta rule (6331). 14 refs., 3 figs.

Research Organization:
Los Alamos National Lab., NM (USA)
Sponsoring Organization:
DOE/MA
DOE Contract Number:
W-7405-ENG-36
OSTI ID:
6698032
Report Number(s):
LA-UR-90-2358; CONF-9007117--3; ON: DE90014926
Country of Publication:
United States
Language:
English

Similar Records

A fast new algorithm for a robot neurocontroller using inverse QR decomposition
Journal Article · Fri Dec 31 23:00:00 EST 1999 · International Journal of Robotics Research · OSTI ID:20005689

Dynamic gradient descent learning algorithms for enhanced empirical modeling of power plants
Conference · Thu Oct 31 23:00:00 EST 1991 · Transactions of the American Nuclear Society; (United States) · OSTI ID:5074299

Discrete mathematics for computer scientists and mathematicians: 2nd ed
Book · Tue Dec 31 23:00:00 EST 1985 · OSTI ID:5205391