DECONSTRUCTIVE LEARNING By MOHSEN ALI A DISSERTATION PRESENTED TO THE GRADUATE SCHOOL OF THE UNIVERSITY OF FLORIDA IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY

of Dissertation Presented to the Graduate School of the University of Florida in Partial Fulfillment of the Requirements for the Degree of Doctor of Philosophy DECONSTRUCTIVE LEARNING By Mohsen Ali May 2014 Chair: Jeffrey Ho Major: Computer Engineering This dissertation introduces the novel notion of deconstructive learning and it proposes a practical computational framework for deconstructing a broad class of binary classifiers commonly used in computer vision applications. While the ultimate objective of most learning problems is the determination of classifiers from labeled training data, for deconstructive learning, the objects of study are the classifiers themselves. As its name suggests, the goal of deconstructive learning is to deconstruct a given classifier by determining and characterizing (as much as possible) the full extent of its capability, revealing all of its powers, subtleties and limitations. In particular, this work is motivated by the seemingly innocuous question that given an image-based binary classifier C as a black-box oracle, how much can we learn of its internal working by simply querying it? To formulate and answer this question computationally, I will first describe a general two-component design model employed by many current computer vision binary classifiers, a clear demonstration of the division of labor between practitioners in computer vision and machine learning. In this model, an input image is first transformed via a (nonlinear) feature transform to a feature space and a classifier is applied to the transformed feature to produce the classification output. The deconstruction of such a classifier therefore aims to identify the specific feature transform and the feature-space classifier used in the model.