Understanding Representations and Reducing their Redundancy in Deep Networks
Neural networks in their modern deep learning incarnation have achieved state of the art performance on a wide variety of tasks and domains. A core intuition behind these methods is that they learn layers of features which interpolate between two domains in a series of related parts. The first part...
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | en_US |
| Published: |
Virginia Tech
2017
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10919/78167 http://scholar.lib.vt.edu/theses/available/etd-03032016-170427/ |