Convolutional restricted boltzmann machines for feature learning
Mohammad Norouzi · Summit (Simon Fraser University) · 2009
In this thesis, we present a probabilistic generative approach for learning hierarchical structures 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 demonstrated 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. IIIThis is a great opportunity for me to publicly thank those who have been influential during my studies at Simon Fraser University.I am grateful to God who gave me this wonderful life and continuously showers me with blessings.I am profoundly indebted to my supervisor, Dr. Greg Mori, because of his calmness, endless support, and deep insights.Whenever I was disappointed of the ideas or experimental results, he inspired me to try harder.I thank my Mom and Dad, Mansoureh