Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp01pn89d9370
 Title: Optimization of Mutual Information in Learning: Explorations in Science Authors: Strouse, Daniel Advisors: Schwab, David JBialek, William Contributors: Physics Department Subjects: Artificial intelligence Issue Date: 2018 Publisher: Princeton, NJ : Princeton University Abstract: This thesis explores three applications of information theory in machine learning, all involving the optimization of information flow in some learning problem. In Chapter 2, we introduce a method for extracting the most informative bits that one signal contains about another. Our method, the deterministic information bottleneck (DIB), is an alternative formulation of the information bottleneck (IB). In Chapter 3, we adapt the DIB to the problem of finding the most informative clusterings of geometric data. We also introduce an approach to model selection that naturally emerges within the (D)IB framework. In Chapter 4 we introduce an approach to encourage / discourage agents in a multi-agent reinforcement learning setting to share information with one another. We conclude in Chapter 5 by discussing ongoing and future work in these directions. URI: http://arks.princeton.edu/ark:/88435/dsp01pn89d9370 Alternate format: The Mudd Manuscript Library retains one bound copy of each dissertation. Search for these copies in the library's main catalog: catalog.princeton.edu Type of Material: Academic dissertations (Ph.D.) Language: en Appears in Collections: Physics

Files in This Item:
File Description SizeFormat
Strouse_princeton_0181D_12733.pdf10.83 MBAdobe PDF

Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.