Robust Visual Recognition Using Multilayer Generative Neural Networks
Deep generative neural networks such as the Deep Belief Network and Deep Boltzmann Machines have been used successfully to model high dimensional visual data. However, they are not robust to common variations such as occlusion and random noise. In this thesis, we explore two strategies for improving...
| Main Author: | |
|---|---|
| Language: | en |
| Published: |
2010
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10012/5376 |