Parallel-cascaded noniterative neural network for identfying closely related optical patterns

Chia-Lun John Hu

doi:10.1117/12.381605

31 March 2000 Parallel-cascaded noniterative neural network for identfying closely related optical patterns

Chia-Lun John Hu

Proceedings Volume 4043, Optical Pattern Recognition XI; (2000) https://doi.org/10.1117/12.381605
Event: AeroSense 2000, 2000, Orlando, FL, United States

Abstract

When the training class patterns {U_m} are closely related and they are inseparable (according to some targeted binary output vectors {V_m}) by a one- layered perceptron (OLP), then {U_m} must be linearly dependent, and the output-augmented {U_m} must be positively, linearly dependent. The learning of this OLP is then impossible no matter what learning rules we use, because the solution of the connection matrix just does not exist. However, we can always use a parallel-cascaded, two-layered perceptron (PCTLP) to realize this inseparable mapping. The design of this PCTLP is derived from the positive-linear independency condition we previously studied. It is a very intriguing mathematical derivation and the design of the PCTLP is much more efficient then that of the conventional series- cascaded, three-layered, neural networks. Also its robustness in recognizing any untrained, closely related patterns can be controlled and maximized. The physical origin, the theory, and the design of this novel, `universal' perceptron pattern recognition system will be discussed in detail in this paper.

Citation Download Citation

Chia-Lun John Hu "Parallel-cascaded noniterative neural network for identfying closely related optical patterns", Proc. SPIE 4043, Optical Pattern Recognition XI, (31 March 2000); https://doi.org/10.1117/12.381605

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