Back Propagation On Warp

George L. Gusciora

doi:10.1117/12.948568

16 December 1989 Back Propagation On Warp

George L. Gusciora

Proceedings Volume 0977, Real-Time Signal Processing XI; (1989) https://doi.org/10.1117/12.948568
Event: 32nd Annual International Technical Symposium on Optical and Optoelectronic Applied Science and Engineering, 1988, San Diego, CA, United States

Abstract

We describe two fast back-propagation algorithms for a linear array of processors. Results of the implementation of both algorithms on Warp, a ten processor, programmable systolic array computer, are reviewed and compared with back-propagation implementations on other machines. Our fastest Warp simulator is about 11 times faster at simulating the NETtaik text-to-speech network than the fastest back-propagation simulator previously reported in the literature. This fast simulator on Warp is being used routinely in autonomous navigation experiments, image processing experiments and speech recognition experiments at Carnegie Mellon. Our results indicate that linear systolic array machines can be efficient neural network simulators.

Citation Download Citation

George L. Gusciora "Back Propagation On Warp", Proc. SPIE 0977, Real-Time Signal Processing XI, (16 December 1989); https://doi.org/10.1117/12.948568

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