Title :
A new implementation of discrete-time Hopfield net with higher capacity and speed of convergence
Author :
Menhaj, Mohammad B. ; Seifipour, Navid
Author_Institution :
Dept. of Electr. Eng., Amirkabir Univ., Tehran, Iran
Abstract :
The Hopfield network with a recurrent, non-hierarchical structure is an effective tool for associative memories as well as for optimizations. The main drawback of discrete-time Hopfield net is its low limit of storage capacity. This paper presents a new implementation of Hopfield structured neural net processing higher storage capacities and higher speed rate of convergence as well
Keywords :
Hopfield neural nets; content-addressable storage; convergence; optimisation; Hopfield neural network; associative memory; convergence; discrete-time Hopfield net; optimization; recurrent neural net; Associative memory; Convergence; Energy storage; Limit-cycles; Network synthesis; Neural networks; Neurons; Recurrent neural networks; State-space methods; Time measurement;
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN '01. International Joint Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.939059
