Share Email Print

Proceedings Paper

Temporal generalization capability of simple recurrent networks
Author(s): Xiaomei Liu; DeLiang Wang; Stanley C. Ahalt
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 6 April 1995
PDF: 12 pages
Proc. SPIE 2492, Applications and Science of Artificial Neural Networks, (6 April 1995); doi: 10.1117/12.205145
Show Author Affiliations
Xiaomei Liu, The Ohio State Univ. (United States)
DeLiang Wang, The Ohio State Univ. (United States)
Stanley C. Ahalt, The Ohio State Univ. (United States)

Published in SPIE Proceedings Vol. 2492:
Applications and Science of Artificial Neural Networks
Steven K. Rogers; Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?