Recognizing the untrained patterns in a noniterative perceptron learning scheme

Chia-Lun John Hu; Jeng-Yoong Tan; Xue-Jiang Cheng; John R. Eynon; Osama Husson

doi:10.1117/12.152621

19 August 1993 Recognizing the untrained patterns in a noniterative perceptron learning scheme

Chia-Lun John Hu, Jeng-Yoong Tan, Xue-Jiang Cheng, John R. Eynon, Osama Husson

Proceedings Volume 1966, Science of Artificial Neural Networks II; (1993) https://doi.org/10.1117/12.152621
Event: Optical Engineering and Photonics in Aerospace Sensing, 1993, Orlando, FL, United States

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.

Citation Download Citation

Chia-Lun John Hu, Jeng-Yoong Tan, Xue-Jiang Cheng, John R. Eynon, and Osama Husson "Recognizing the untrained patterns in a noniterative perceptron learning scheme", Proc. SPIE 1966, Science of Artificial Neural Networks II, (19 August 1993); https://doi.org/10.1117/12.152621

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available