dc.contributor.advisor | Kak, Subhash C. | |
dc.contributor.author | Reddy, Gangasani Sumanth Kumar | |
dc.date.accessioned | 2014-04-15T18:31:04Z | |
dc.date.available | 2014-04-15T18:31:04Z | |
dc.date.issued | 2008-12-01 | |
dc.identifier.uri | https://hdl.handle.net/11244/8149 | |
dc.description.abstract | The prescriptive learning and generalization capabilities of the instantaneously trained neural networks make them suitable for various applications. Although the CC4 network, which is the most popular of the instantaneously trained neural networks, does well in comparison with the back propagation network, it suffers from several implementation issues when applied to large data sets. To address these issues, we present a generalized CC4 network. We also describe single neuron implementations of the new network which improve the flexibility and performance of the network. We present results of applications of this network to image processing and time-series prediction. | |
dc.format | application/pdf | |
dc.language | en_US | |
dc.publisher | Oklahoma State University | |
dc.rights | Copyright is held by the author who has granted the Oklahoma State University Library the non-exclusive right to share this material in its institutional repository. Contact Digital Library Services at lib-dls@okstate.edu or 405-744-9161 for the permission policy on the use, reproduction or distribution of this material. | |
dc.title | Generalization and Efficient Implementation of CC4 Neural Network | |
dc.type | text | |
dc.contributor.committeeMember | Park, Nohpill | |
dc.contributor.committeeMember | Sarangan, Venkatesh | |
osu.filename | Gangasani_okstate_0664M_10140.pdf | |
osu.college | Arts and Sciences | |
osu.accesstype | Open Access | |
dc.description.department | Computer Science Department | |
dc.type.genre | Thesis | |