Abstract
The method of generalized projections is applied to the multilayer feed-forward neural-net problem to derive a new learning algorithm.1 Unfortunately, strict adherence to the learning rule requires the solution of coupled, nonlinear algebraic equations. By permitting a simplification, a new learning rule results, which produces an implementable algorithm. We call this learning rule the projection-method learning rule (PMLR). We apply the PMLR to two well-known pattern-recognition problems, neither of which is solvable by a linear-discriminant scheme. The PMLR is compared with the error-back-propagation learning rule (BPLR) and is shown to converge faster than the BPLR for the problems being considered.
© 1990 Optical Society of America
PDF ArticleMore Like This
Francis T. S. Yu, Taiwei Lu, and Don A. Gregory
MB4 Spatial Light Modulators and Applications (SLM) 1990
David Casasent
MJJ1 OSA Annual Meeting (FIO) 1990
P. Asthana, H. Chin, G. Nordin, A. R. Tanguay, G. C. Petrisor, B. K. Jenkins, and A. Madhukar
MVV4 OSA Annual Meeting (FIO) 1990