Title :
A temporal neural system
Author :
Heeb, Jay ; Akers, Lex A.
Author_Institution :
Center for Solid State Electron. Res., Arizona State Univ., Tempe, AZ, USA
fDate :
30 May-2 Jun 1994
Abstract :
Time is often the dominant information dimension. Applications for time-dependent adaptive systems include sequence generation and predication, image processing, and dynamic control. We have developed a temporal neural system which is composed of an architecture, processing nodes, and training algorithm. The architecture allows arbitrary connectivity between processing nodes including recurrent connections. The processing node includes higher order conjunctive terms, and the training algorithm allows arbitrarily configured topologies to be trained. We demonstrate the temporal neural system by simulating time series generation and a finite state machine
Keywords :
adaptive systems; finite state machines; learning (artificial intelligence); recurrent neural nets; temporal reasoning; time series; arbitrarily configured topologies; arbitrary connectivity; dynamic control; finite state machine; higher order conjunctive terms; image processing; recurrent connections; sequence generation; temporal neural system; time series generation; time-dependent adaptive systems; training algorithm; Adaptive control; Convolution; Image generation; Image processing; Network topology; Neural networks; Neurons; Process control; Programmable control; Signal processing algorithms;
Conference_Titel :
Circuits and Systems, 1994. ISCAS '94., 1994 IEEE International Symposium on
Conference_Location :
London
Print_ISBN :
0-7803-1915-X
DOI :
10.1109/ISCAS.1994.409580
