Title :
Short term memory structures for dynamic neural networks
Author :
De Vries, Bert ; Principe, Jose C.
Author_Institution :
David Sarnoff Res. Center, Princeton, NJ, USA
Abstract :
A framework for designing and characterizing short-term memory structures for neural networks is presented. The gamma memory, a recursive linear structure, is presented as a generalization of the tapped delay line or the context memory units. The gamma memory principle can be enhanced to construct nonuniform time warping scales that may be useful in speech recognition
Keywords :
neural nets; context memory units; dynamic neural networks; gamma memory; nonuniform time warping scales; recursive linear structure; short-term memory structures; speech recognition; tapped delay line; Computer networks; Delay lines; Design methodology; Error analysis; Neural engineering; Neural networks; Nonlinear filters; Protocols; Signal design; Speech recognition;
Conference_Titel :
Signals, Systems and Computers, 1992. 1992 Conference Record of The Twenty-Sixth Asilomar Conference on
Conference_Location :
Pacific Grove, CA
Print_ISBN :
0-8186-3160-0
DOI :
10.1109/ACSSC.1992.269169
