Title :
Prediction of dynamical phenomena by a neural network
Author_Institution :
Fac. of Mech. Eng., Ljubljana Univ., Yugoslavia
Abstract :
An adaptive information processing system capable of predicting dynamical phenomena is described. It includes a neural network-like memory, a predictor, two shift registers, and a comparator. In the memory, an internal empirical model of observed phenomena is formed. It is described by a set of memorized prototype transitions between successive states of an input time-dependent signal which can also be chaotic. System operation is demonstrated on a chaotic signal generated by the Henon map
Keywords :
adaptive systems; chaos; content-addressable storage; filtering and prediction theory; neural nets; Henon map; adaptive information processing system; chaotic signal; comparator; dynamical phenomena; input time-dependent signal; internal empirical model; memorized prototype transitions; neural network; neural network-like memory; predictor; shift registers; Adaptive systems; Chaos; Information processing; Mechanical engineering; Neural networks; Neurons; Prototypes; Sensor phenomena and characterization; Shift registers; State-space methods;
Conference_Titel :
Electrotechnical Conference, 1991. Proceedings., 6th Mediterranean
Conference_Location :
LJubljana
Print_ISBN :
0-87942-655-1
DOI :
10.1109/MELCON.1991.161770
