19 August 1993 Recognizing the untrained patterns in a noniterative perceptron learning scheme
Author Affiliations +
Abstract
As we reported previously, a deterministic hard-limited perceptron is a novel learning system in which the learning mechanism is different from most of the conventional learning systems. It is a noniterative, one-step learning system and yet is achieves most of the goals of the conventional learning. If an optimum algorithm is adopted in the design of this learning system, the learning is very fast and the recognition is very robust. This article reports the experimental results of several computer-implemented schemes of this novel learning system. It is seen that the system takes only one to two minutes to train several given patterns and the recognition of the untrained patterns is more than 80% successful. In one scheme, the recognition rate is almost 100% and the recognition is independent of the pattern size, pattern orientation, and pattern location.
© (1993) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chia-Lun John Hu, Jeng-Yoong Tan, Xue-Jiang Cheng, John R. Eynon, Osama Husson, "Recognizing the untrained patterns in a noniterative perceptron learning scheme", Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); doi: 10.1117/12.152621; https://doi.org/10.1117/12.152621
PROCEEDINGS
7 PAGES


SHARE
RELATED CONTENT

Multiresolution neural networks
Proceedings of SPIE (March 15 1994)
Neural networks as components
Proceedings of SPIE (July 01 1992)
Grand challenges
Proceedings of SPIE (March 30 2000)

Back to Top