ATTENTION: The works hosted here are being migrated to a new repository that will consolidate resources, improve discoverability, and better show UTA's research impact on the global community. We will update authors as the migration progresses. Please see MavMatrix for more information.
Show simple item record
dc.contributor.author | Challagundla, Jeshwanth | en_US |
dc.date.accessioned | 2015-07-31T22:10:05Z | |
dc.date.available | 2015-07-31T22:10:05Z | |
dc.date.submitted | January 2015 | en_US |
dc.identifier.other | DISS-13059 | en_US |
dc.identifier.uri | http://hdl.handle.net/10106/25030 | |
dc.description.abstract | There is always an ambiguity in deciding the number of learning factors that is really required for training a Multi-Layer Perceptron. This thesis solves this problem by introducing a new method of adaptively changing the number of learning factors computed based on error change created per multiply. A new method is introduced for computing learning factors for weights grouped based on the curvature of the objective function. A method for linearly compressing large ill-conditioned Newton's Hessian matrices to smaller well-conditioned ones is shown. This thesis also shows that the proposed training algorithm adapts itself between two other algorithms in order to produce a better error decrease per multiply. The performance of the proposed algorithm is shown to be better than OWO-MOLF and Levenberg Marquardt for most of the data sets. | en_US |
dc.description.sponsorship | Manry, Michael T. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Electrical Engineering | en_US |
dc.title | Adaptive Multiple Optimal Learning Factors For Neural Network Training | en_US |
dc.type | M.S. | en_US |
dc.contributor.committeeChair | Manry, Michael T. | en_US |
dc.degree.department | Electrical Engineering | en_US |
dc.degree.discipline | Electrical Engineering | en_US |
dc.degree.grantor | University of Texas at Arlington | en_US |
dc.degree.level | masters | en_US |
dc.degree.name | M.S. | en_US |
Files in this item
- Name:
- Challagundla_uta_2502M_13059.pdf
- Size:
- 790.1Kb
- Format:
- PDF
This item appears in the following Collection(s)
Show simple item record