Return to search

Learning Deep Generative Models

Building intelligent systems that are capable of extracting high-level representations from high-dimensional sensory data lies at the core of solving many AI related tasks, including object recognition, speech perception, and language understanding. Theoretical and biological arguments strongly suggest that building such systems requires models with deep architectures that involve many layers of nonlinear processing. The aim of the thesis is to demonstrate that deep generative models that contain many layers of latent variables and millions of parameters can be learned efficiently, and that the learned high-level feature representations can be successfully applied in a wide spectrum of application domains, including visual object recognition, information retrieval, and classification and regression tasks. In addition, similar methods can be used for nonlinear dimensionality reduction.

Identiferoai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:OTU.1807/19226
Date02 March 2010
CreatorsSalakhutdinov, Ruslan
ContributorsHinton, Geoffrey
Source SetsLibrary and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada
Languageen_ca
Detected LanguageEnglish
TypeThesis

Page generated in 0.0017 seconds