29 October 1993 Feature competition and domain of attraction in artificial-perceptron pattern recognizer
Author Affiliations +
Abstract
As we reported previously, learning of a multi-layered hard-limited perceptron can be formulated into a set of simultaneous linear inequalities. Solving these inequalities under a given training set would then allow us to achieve the goal of learning in this system. If the dimension N of the input vector is much larger than the number M of different patterns to be learned, then there is considerable freedom for the system to select a proper solution of the connection matrix. In most cases, even a single layer perceptron will do the learning satisfactorily. This paper reports the results of some theoretical and experimental studies of this one-layered, hard-limited perceptron trained under the novel, one-step, noniterative learning scheme. Particularly, the analysis of some important properties of this novel learning system, such as automatic feature competition, domain of convergence, and robustness of recognition, are discussed in detail.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chia-Lun John Hu, Chia-Lun John Hu, } "Feature competition and domain of attraction in artificial-perceptron pattern recognizer", Proc. SPIE 2032, Neural and Stochastic Methods in Image and Signal Processing II, (29 October 1993); doi: 10.1117/12.162025; https://doi.org/10.1117/12.162025
PROCEEDINGS
4 PAGES


SHARE
RELATED CONTENT

Multiresolution neural networks
Proceedings of SPIE (March 14 1994)
Hybrid neural networks for gray image recognition
Proceedings of SPIE (August 18 1998)
Novel geometrical supervised-learning scheme
Proceedings of SPIE (July 31 1990)
Optimal robustness in noniterative learning
Proceedings of SPIE (April 05 1995)

Back to Top