University of Waterloo
Robust Visual Recognition Using Multilayer Generative Neural Networks
Abstract
dc:description.abstractDeep 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 the robustness of DBNs. First, we show that a DBN with sparse connections in the first layer is more robust to variations that are not in the training set. Second, we develop a probabilistic denoising algorithm to determine a subset of the hidden layer nodes to unclamp. We show that this can be applied to any feedforward network classifier with localized first layer connections. By utilizing the already available generative model for denoising prior to recognition, we show significantly better performance over the standard DBN implementations for various sources of noise on the standard and Variations MNIST databases.
Degree
thesis:*- Grantor dc:publisher
- University of Waterloo
- Year dc:date.issued
- 2010
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Tang, Yichuan
Subjects
dc:subject × 2Rights
- Language dc:language.iso
- en
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- http://hdl.handle.net/10012/5376