dc.contributor.advisor | Kak, Subhash C. | |
dc.contributor.author | Lingashetty, Krishna Chaithanya | |
dc.date.accessioned | 2014-04-15T18:32:59Z | |
dc.date.available | 2014-04-15T18:32:59Z | |
dc.date.issued | 2010-07-01 | |
dc.identifier.uri | https://hdl.handle.net/11244/8195 | |
dc.description.abstract | This thesis is concerned with the problem of memory recall for the feedback neural network called the B-Matrix network. A new model -- the Active Sites model -- is proposed to reduce the computational complexity of the B-Matrix approach. We also develop a new delta learning rule that increases the memory retrieval capacity of the Active Sites model. These techniques are extended to a multi-level, non-binary neural network, which has a much higher capacity than the binary network. Through simulations and analysis, it is demonstrated that to retrieve a memory from a neural network, one does not need to have the whole memory and, as in real life, a fragment of that memory may be sufficient to recall it. | |
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 | Active Sites Implementation for the B-Matrix Neural Network | |
dc.type | text | |
dc.contributor.committeeMember | Chandler, John P. | |
dc.contributor.committeeMember | Toulouse, Michel | |
osu.filename | Lingashetty_okstate_0664M_11057.pdf | |
osu.college | Arts and Sciences | |
osu.accesstype | Open Access | |
dc.description.department | Computer Science Department | |
dc.type.genre | Thesis | |
dc.subject.keywords | active sites | |
dc.subject.keywords | b matrix | |
dc.subject.keywords | delta rule | |
dc.subject.keywords | memory retrieval | |