Title :
Minimum searching by extended Hopfield model
Author :
Matsui, Nobuyuki ; Nakabayashi, Kouichi
Author_Institution :
Dept. of Comput. Eng., Himeji Inst. of Technol., Hyogo, Japan
Abstract :
An extended model of the Hopfield network is presented. The energy function of the authors´ model is given by a cubic expression of neuron-outputs. It is found this energy function converges with frustration and evades efficiently falling into local minima. If is also shown that the extended Hopfield model can produce an efficient and simple method for solving optimization problems
Keywords :
Hopfield neural nets; optimisation; cubic expression; energy function; extended Hopfield model; minimum searching; neuron-outputs; optimization problems; Biological system modeling; Biology computing; Cities and towns; Computer networks; Electronic mail; Neural networks; Neurons; Optimization methods; Power engineering and energy; Symmetric matrices;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487828
