| | | Document Type | : | Latin Dissertation | | Language of Document | : | English | | Record Number | : | 53421 | | Doc. No | : | TL23375 | | Call number | : | MS23461 | | Main Entry | : | Mohammad Norouzi | | Title & Author | : | Convolutional Restricted Boltzmann Machines for Feature LearningMohammad Norouzi | | College | : | Simon Fraser University (Canada) | | Date | : | 2009 | | Degree | : | M.S. | | student score | : | 2009 | | Page No | : | 63 | | Abstract | : | In this thesis, we present a probabilistic generative approach for learning hierarchical struc- tures of spatially local features, effective for visual recognition. Recently, a greedy layerwise learning mechanism has been proposed for training fully-connected neural networks. This mechanism views each of the network’s layers as a Restricted Boltzmann Machines (RBM), and trains them separately and bottom-up. We develop Convolutional RBM (CRBM), in which connections are local and weights are shared to respect the spatial structure of images. We train a hierarchy of visual feature detectors in layerwise manner by switching between the CRBM models and down-sampling layers. Our model learns generic gradient features at the bottom layers and class-specific features in the top levels. It is experimentally demon- strated that the features automatically learned by our algorithm are effective for visual recognition tasks, by using them to obtain performance comparable to the state-of-the-art on handwritten digit classification and pedestrian detection. | | Subject | : | Applied sciences; Computer science; 0984:Computer science | | Added Entry | : | A. A. Bulatov | | Added Entry | : | Simon Fraser University (Canada) |
| | | | | |
| | |  |
http://lib.clisel.com/site/catalogue/53421
| | | |
| | | |
|