DocumentCode :
2404568
Title :
Locally recurrent networks with multiple time-scales
Author :
Juan, Jui-Kuo ; Harris, John G. ; Principe, Jose C.
Author_Institution :
Comput. Neuro-Eng. Lab., Florida Univ., Gainesville, FL, USA
fYear :
1997
fDate :
24-26 Sep 1997
Firstpage :
645
Lastpage :
653
Abstract :
We introduce a new generalized feedforward structure that provides for multiple time scales. The gamma, Laguerre and other locally recurrent feedforward structures perform poorly in cases where widely varying time constants are required. By exponentially varying the time-constant along the delay line, a single delay line is able to represent signals that include various time scales. We demonstrate both discrete- and continuous-time versions of this multiple time-scale structure which we call the multi-scale gamma filter. The multi-scale gamma has a very natural implementation in sub-threshold CMOS and measured impulse responses from a continuous-time analog VLSI chip are shown
Keywords :
CMOS analogue integrated circuits; IIR filters; VLSI; continuous time filters; discrete time filters; feedforward neural nets; neural chips; recurrent neural nets; CMOS; analog VLSI chip; continuous-time filter; delay line; discrete time filter; feedforward neural networks; impulse responses; locally recurrent networks; multiple time-scales; multiscale gamma filter; Delay lines; Digital filters; Feedforward systems; Finite impulse response filter; Hardware; Laboratories; Measurement standards; Neural engineering; Semiconductor device measurement; Very large scale integration;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks for Signal Processing [1997] VII. Proceedings of the 1997 IEEE Workshop
Conference_Location :
Amelia Island, FL
ISSN :
1089-3555
Print_ISBN :
0-7803-4256-9
Type :
conf
DOI :
10.1109/NNSP.1997.622447
Filename :
622447
Link To Document :
بازگشت