| dc.contributor.author | Singh, Jayant | |
| dc.description.abstract | We consider the method of Reduction of Dissipativity Domain to prove global Lyapunov
stability of Discrete Time Recurrent Neural Networks. The standard and advanced criteria for
Absolute Stability of these essentially nonlinear systems produce rather weak results. The method
mentioned above is proved to be more powerful. It involves a multi-step procedure with maximization
of special nonconvex functions over polytopes on every step. We derive conditions which
guarantee an existence of at most one point of local maximum for such functions over every hyperplane.
This nontrivial result is valid for wide range of neuron transfer functions. | en_US |
| dc.publisher | North Dakota State University | en_US |
| dc.rights | NDSU Policy 190.6.2 | |
| dc.title | Optimization Problems Arising in Stability Analysis of Discrete Time Recurrent Neural Networks | en_US |
| dc.type | Dissertation | en_US |
| dc.type | Video | en_US |
| dc.date.accessioned | 2016-01-22T21:13:46Z | |
| dc.date.available | 2016-01-22T21:13:46Z | |
| dc.date.issued | 2016 | |
| dc.identifier.uri | http://hdl.handle.net/10365/25537 | |
| dc.rights.uri | https://www.ndsu.edu/fileadmin/policy/190.pdf | |
| ndsu.degree | Doctor of Philosophy (PhD) | en_US |
| ndsu.college | Science and Mathematics | en_US |
| ndsu.department | Mathematics | en_US |
| ndsu.program | Mathematics | en_US |
| ndsu.advisor | Barabanov, Nikita | |
