Modified Newton's method for supervised training of dynamical neural networks for applications in associative memory and nonlinear identification problems
| dc.contributor.advisor | Sundareshan, Malur K. | en_US |
| dc.contributor.author | Bhalala, Smita Ashesh, 1966- | |
| dc.creator | Bhalala, Smita Ashesh, 1966- | en_US |
| dc.date.accessioned | 2013-04-03T13:08:06Z | |
| dc.date.available | 2013-04-03T13:08:06Z | |
| dc.date.issued | 1991 | en_US |
| dc.identifier.uri | http://hdl.handle.net/10150/277969 | |
| dc.description.abstract | There have been several innovative approaches towards realizing an intelligent architecture that utilizes artificial neural networks for applications in information processing. The development of supervised training rules for updating the adjustable parameters of neural networks has received extensive attention in the recent past. In this study, specific learning algorithms utilizing modified Newton's method for the optimization of the adjustable parameters of a dynamical neural network are developed. Computer simulation results show that the convergence performance of the proposed learning schemes match very closely that of the LMS learning algorithm for applications in the design of associative memories and nonlinear mapping problems. However, the implementation of the modified Newton's method is complex due to the computation of the slope of the nonlinear sigmoidal function, whereas, the LMS algorithm approximates the slope to be zero. | |
| dc.language.iso | en_US | en_US |
| dc.publisher | The University of Arizona. | en_US |
| dc.rights | Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author. | en_US |
| dc.subject | Engineering, Electronics and Electrical. | en_US |
| dc.subject | Artificial Intelligence. | en_US |
| dc.subject | Computer Science. | en_US |
| dc.title | Modified Newton's method for supervised training of dynamical neural networks for applications in associative memory and nonlinear identification problems | en_US |
| dc.type | text | en_US |
| dc.type | Thesis-Reproduction (electronic) | en_US |
| thesis.degree.grantor | University of Arizona | en_US |
| thesis.degree.level | masters | en_US |
| dc.identifier.proquest | 1345608 | en_US |
| thesis.degree.discipline | Graduate College | en_US |
| thesis.degree.name | M.S. | en_US |
| dc.identifier.bibrecord | .b27056028 | en_US |
| refterms.dateFOA | 2018-06-17T23:52:36Z | |
| html.description.abstract | There have been several innovative approaches towards realizing an intelligent architecture that utilizes artificial neural networks for applications in information processing. The development of supervised training rules for updating the adjustable parameters of neural networks has received extensive attention in the recent past. In this study, specific learning algorithms utilizing modified Newton's method for the optimization of the adjustable parameters of a dynamical neural network are developed. Computer simulation results show that the convergence performance of the proposed learning schemes match very closely that of the LMS learning algorithm for applications in the design of associative memories and nonlinear mapping problems. However, the implementation of the modified Newton's method is complex due to the computation of the slope of the nonlinear sigmoidal function, whereas, the LMS algorithm approximates the slope to be zero. |
