Title :
Ambiguously fluctuating associative memory model with hysteresis dependency
Author_Institution :
ATR Human Inf. Process. Res. Labs., Kyoto, Japan
Abstract :
This paper proposes a new associative memory model based on an oscillatory neural network for a dynamic recognition process. A state space is partitioned by various attractor basins of stable points, limit cycles and chaos, etc., according to the initial state and property of hysteresis. The ambiguously fluctuating output is affected not only by the initial input state, but also by the prediction from the context thorough the prior input sequences.
Keywords :
associative processing; chaos; content-addressable storage; hysteresis; limit cycles; neural nets; state-space methods; ambiguously fluctuating output; associative memory model; attractor basins; chaos; dynamic recognition process; hysteresis dependency; limit cycles; oscillatory neural network; stable points; state space; Associative memory; Biological neural networks; Brain modeling; Chaos; Context modeling; Hysteresis; Information processing; Limit-cycles; Neural networks; State-space methods;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714190