A new learning method for S-GCM

Authors:
Hamed Rahimov;Mohammad-Reza Jahedmotlagh;Nasser Mozayani
Affiliations:
Computer Engineering Faculty, Iran University of Science and Technology, Tehran, Iran;Computer Engineering Faculty, Iran University of Science and Technology, Tehran, Iran;Computer Engineering Faculty, Iran University of Science and Technology, Tehran, Iran
Venue:
AI'06 Proceedings of the 19th Australian joint conference on Artificial Intelligence: advances in Artificial Intelligence
Year:
2006

Citing 6
Cited 0

Clustering, coding, switching, hierarchical ordering, and control in a network of chaotic elements

Physica D
Chaotic simulated annealing by a neural network model with transient chaos

Neural Networks
A network of chaotic elements for information processing

Neural Networks
Associative memory based on parametrically coupled chaotic elements

Physica D
The Study of Chaotic Neural Network and its Applications in Associative Memory

Neural Processing Letters
A new parameter control method for S-GCM

Pattern Recognition Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

One of artificial neural network models with non-equilibrium dynamics is S-GCM. This model in comparison to Hopfield method has more capacity storage and more success rate, but yet, as an associative memory system has some weakness such as small storage rate and low speed of convergence. In this paper, a new learning method for S-GCM is proposed. In the proposed method, we use modified sparse matrix for learning method. Both the theory analyses and computer simulation results show that the performance of S-GCM can be improved greatly by using our learning method.