Temporal generalization capability of simple recurrent networks

Xiaomei Liu; DeLiang Wang; Stanley C. Ahalt

doi:10.1117/12.205145

6 April 1995 Temporal generalization capability of simple recurrent networks

Xiaomei Liu, DeLiang Wang, Stanley C. Ahalt

Proceedings Volume 2492, Applications and Science of Artificial Neural Networks; (1995) https://doi.org/10.1117/12.205145
Event: SPIE's 1995 Symposium on OE/Aerospace Sensing and Dual Use Photonics, 1995, Orlando, FL, United States

Abstract

Simple recurrent networks have been widely used in temporal processing applications. In this study we investigate temporal generalization of simple recurrent networks, drawing comparisons between network capabilities and human characteristics. Elman networks were trained to regenerate temporal trajectories sampled at different rates, and then tested with trajectories at both the trained sampling rates and at other sampling rates. The networks were also tested with trajectories representing mixtures of different sampling rates. It was found that for simple trajectories, the networks show interval invariance, but not rate invariance. However, for complex trajectories which contain greater contextual information, these networks do not seem to show any temporal generalization. Similar results were also obtained employing measured speech data. Thus, these results suggest that this class of networks exhibits severe limitations in temporal generalization.

Citation Download Citation

Xiaomei Liu, DeLiang Wang, and Stanley C. Ahalt "Temporal generalization capability of simple recurrent networks", Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); https://doi.org/10.1117/12.205145

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