Abstract | ||
---|---|---|
Artificial neural networks are intended to be used in emerging technologies as information processing systems because their biological equivalents seem to be tolerant to internal failures of computational elements. In this paper, we introduce a measurement which can identify significant neurons of the Local Cluster Neural Network and can be used to increase the fault tolerance of this network architecture. Furthermore, it will be shown that this technique can control the network's complexity. Moreover, by this quality different parameter sets of the network and training techniques can be judged with respect to their fault tolerant properties. |
Year | DOI | Venue |
---|---|---|
2007 | 10.1109/IJCNN.2007.4370950 | 2007 IEEE INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOLS 1-6 |
Keywords | Field | DocType |
fault tolerant,artificial neural network,information processing,emerging technology,network architecture,neural network,fault tolerance | Nervous system network models,Network complexity,Physical neural network,Computer science,Stochastic neural network,Network architecture,Types of artificial neural networks,Time delay neural network,Artificial intelligence,Cellular neural network,Machine learning | Conference |
ISSN | Citations | PageRank |
2161-4393 | 0 | 0.34 |
References | Authors | |
7 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ralf Eickhoff | 1 | 65 | 12.37 |
Sitte, J. | 2 | 182 | 23.99 |