Neural network watchdog for out-of-distribution input mitigation.
| dc.contributor.advisor | Marks, Robert J., II (Robert Jackson), 1950- | |
| dc.creator | Bui, Justin M., 1988- | |
| dc.date.accessioned | 2022-01-28T14:46:41Z | |
| dc.date.available | 2022-01-28T14:46:41Z | |
| dc.date.created | 2021-12 | |
| dc.date.issued | 2021-10-19 | |
| dc.date.submitted | December 2021 | |
| dc.date.updated | 2022-01-28T14:46:43Z | |
| dc.description.abstract | Neural networks have often been described as black boxes. The prevalence of publicly available neural networks and the application of transfer learning has allowed for the development of systems with minimal understanding of the data distribution. For example, a generic neural network trained to differentiate between kittens and puppies will classify a picture of a kumquat as either a kitten or a puppy, despite the kumquat residing outside the known data distribution. The neural network watchdog is a technique which screens trained classifier and regression machine input candidates to determine the distribution validity, and allows for methods of out-of-distribution removal with minimal performance impact. | |
| dc.format.mimetype | application/pdf | |
| dc.identifier.uri | https://hdl.handle.net/2104/11704 | |
| dc.language.iso | en | |
| dc.rights.accessrights | Worldwide access | |
| dc.subject | Neural networks. Machine learning. Watchdog. | |
| dc.title | Neural network watchdog for out-of-distribution input mitigation. | |
| dc.type | Thesis | |
| dc.type.material | text | |
| thesis.degree.department | Baylor University. Dept. of Electrical & Computer Engineering. | |
| thesis.degree.grantor | Baylor University | |
| thesis.degree.level | Doctoral | |
| thesis.degree.name | Ph.D. |
Files
License bundle
1 - 1 of 1