Title :
Probabilistic connections in relaxation networks
Author_Institution :
Dept. of Comput. Sci., Brigham Young Univ., Provo, UT, USA
fDate :
6/24/1905 12:00:00 AM
Abstract :
This paper reports on the results from studying the behavior of Hopfield-type networks with probabilistic connections. As the probabilities decrease, network performance degrades. In order to compensate problem, two network modifications, an input persistence and a new activation function, are suggested and empirical results indicate that the modifications described significantly improve the network performance
Keywords :
Hopfield neural nets; optimisation; performance evaluation; probability; transfer functions; Hopfield-type networks; activation function; input persistence; network performance; network stability; neural networks; probabilistic connections; probability; relaxation networks; Artificial neural networks; Associative memory; Computer science; Degradation; Energy consumption; Equations; Intelligent networks; Mobile agents; Pathology; Time factors;
Conference_Titel :
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location :
Honolulu, HI
Print_ISBN :
0-7803-7278-6
DOI :
10.1109/IJCNN.2002.1005600
