Using quasirandom numbers in neural networks

Show simple item record

dc.contributor.author Anderson, Peter en_US
dc.contributor.author Gaborski, Roger en_US
dc.contributor.author Ge, Ming en_US
dc.contributor.author Raghavendra, Sanjay en_US
dc.contributor.author Lung, Mei-ling en_US
dc.date.accessioned 2006-12-18T17:10:00Z en_US
dc.date.available 2006-12-18T17:10:00Z en_US
dc.date.issued 1995-05-26 en_US
dc.identifier.citation Proceedings of the International ICSC Symposium on Fuzzy Logic (1995) A50-A56 en_US
dc.identifier.isbn 390-64-5400-2 en_US
dc.identifier.uri http://hdl.handle.net/1850/3067 en_US
dc.description "Using Quasirandom Numbers in Neural Networks," Proceedings of the International ICSC Symposium on Fuzzy Logic. ICSC Academic Press. Held at the Swiss Federal Institute of Technology (ETH): Zurich, Switzerland,: May 26-27, 1995. en_US
dc.description.abstract We present a novel training algorithm for a feed forward neural network with a single hidden layer of nodes (i.e., two layers of connection weights). Our algorithm is capable of training networks for hard problems, such as the classic two-spirals problem. The weights in the first layer are determined using a quasirandom number generator. These weights are frozen---they are never modified during the training process. The second layer of weights is trained as a simple linear discriminator using methods such as the pseudo-inverse, with possible iterations. We also study the problem of reducing the hidden layer: pruning low-weight nodes and a genetic algorithm search for good subsets. en_US
dc.description.sponsorship The authors wish to thank Alex Mirzaoff and Eastman Kodak Company for support of this project. en_US
dc.format.extent 460262 bytes en_US
dc.format.mimetype application/pdf en_US
dc.language.iso en_US en_US
dc.publisher International Computing Sciences Conferences (ICSC) en_US
dc.subject Genetic algorithms en_US
dc.subject Neural networks en_US
dc.subject Nodes en_US
dc.subject Quasirandom numbers en_US
dc.title Using quasirandom numbers in neural networks en_US
dc.type Proceedings en_US

Files in this item

Files Size Format View
PAndersonConfProc05-26-1995.pdf 460.2Kb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Search RIT DML


Advanced Search

Browse