Hierarchical learning : theory with applications in speech and vision

Over the past two decades several hierarchical learning models have been developed and applied to a diverse range of practical tasks with much success. Little is known, however, as to why such models work as well as they do. Indeed, most are difficult to analyze, and cannot be easily characterized using the established tools from statistical learning theory. In this thesis, we study hierarchical learning architectures from two complementary perspectives: one theoretical and the other empirical. The theoretical component of the thesis centers on a mathematical framework describing a general family of hierarchical learning architectures. The primary object of interest is a recursively defined feature map, and its associated kernel. The class of models we consider exploit the fact that data in a wide variety of problems satisfy a decomposability property. Paralleling the primate visual cortex, hierarchies are assembled from alternating filtering and pooling stages that build progressively invariant representations which are simultaneously selective for increasingly complex stimuli. A goal of central importance in the study of hierarchical architectures and the cortex alike, is that of understanding quantitatively the tradeoff between invariance and selectivity, and how invariance and selectivity contribute towards providing an improved representation useful for learning from data. A reasonable expectation is that an unsupervised hierarchical representation will positively impact the sample complexity of a corresponding supervised learning task.

Department dc:contributor.department

Massachusetts Institute of Technology. Dept. of Brain and Cognitive Sciences.

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2009

Author dc:creator

• Bouvrie, Jacob V

Advisor dc:contributor.advisor

• Tomaso Poggio.

• Brain and Cognitive Sciences.

Statement dc:rights

• M.I.T. theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. See provided URL for inquiries about permission.

Licence dc:rights.uri

• http://dspace.mit.edu/handle/1721.1/7582

Language dc:language.iso

eng

Handle dc:identifier.uri

http://hdl.handle.net/1721.1/54227

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/54227