Embedding domain information in backpropagation

George M. Georgiou; Cris Koutsougeras

doi:10.1117/12.139948

20 August 1992 Embedding domain information in backpropagation

George M. Georgiou, Cris Koutsougeras

Proceedings Volume 1706, Adaptive and Learning Systems; (1992) https://doi.org/10.1117/12.139948
Event: Aerospace Sensing, 1992, Orlando, FL, United States

Abstract

The search space for backpropagation (BP) is usually of high dimensionality which shows convergence. Also, the number of minima abound, and thus the danger to fall in a shallow one is great. In order to limit the search space of BP in a sensible way, we incorporate domain knowledge in the training process. A Two-phase Backpropagation algorithms is presented. In the first phase the direction of the weight vectors of the first (and possibly the only) hidden layer are constrained to remain in the same directions as, for example, the ones of linear discriminants or Principal Components. The directions are chosen based on the problem at hand. Then in the second phase, the constraints are removed and standard Backpropagation algorithm takes over to further minimize the error function. The first phase swiftly situates the weight vectors in a good position (relatively low error) which can serve as the initialization of the standard Backpropagation. Other speed-up techniques can be used in both phases. The generality of its application, its simplicity, and the shorter training time it requires, make this approach attractive.

Citation Download Citation

George M. Georgiou and Cris Koutsougeras "Embedding domain information in backpropagation", Proc. SPIE 1706, Adaptive and Learning Systems, (20 August 1992); https://doi.org/10.1117/12.139948

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