DocumentCode
1648697
Title
Probabilistic connections in relaxation networks
Author
Ventura, Dan
Author_Institution
Dept. of Comput. Sci., Brigham Young Univ., Provo, UT, USA
Volume
1
fYear
2002
fDate
6/24/1905 12:00:00 AM
Firstpage
934
Lastpage
938
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;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks, 2002. IJCNN '02. Proceedings of the 2002 International Joint Conference on
Conference_Location
Honolulu, HI
ISSN
1098-7576
Print_ISBN
0-7803-7278-6
Type
conf
DOI
10.1109/IJCNN.2002.1005600
Filename
1005600
Link To Document