Online Learning Algorithms For Sequence Prediction, Importance Weighted Classification, And Active Learning
This thesis studies three problems in online learning. For all the problems the proposed solutions are simple yet non-trivial adaptations of existing online machine learning algorithms. For the task of sequential prediction, a modified multiplicative update algorithm that produces small and accurate models is proposed. This algorithm makes no assumption about the complexity of the source that produces the given sequence. For the task of online learning when examples have varying importances, the proposed algorithm is a version of gradient descent in continuous time. Finally, for the task of efficient online active learning, the implementation we provide makes use of many shortcuts. These include replacing a batch learning algorithm with an online one, as well as a creative use of the aforementioned continuous time gradient descent to compute the desirability of asking for the label of a given example. As this thesis shows, online machine learning algorithms can be easily adapted to many new problems.
machine learning; online learning; active learning
Kozen, Dexter Campbell
Hooker, Giles J.; Joachims, Thorsten; Kleinberg, Robert David
Ph. D., Computer Science
Doctor of Philosophy
dissertation or thesis
Showing items related by title, author, creator and subject.
An odyssey through sight, sound, and touch: Toward a perceptual theory of implicit statistical learning Conway, Christopher (American Psychological Association, 2005-07-27)In order to steer through a world characterized by a complex mixture of variability and structure, organisms rely upon implicit statistical learning, the capability to extract probabalistic patterns occurring in environmental ...
Problem-based Learning in Graduate Management Education: An Integrative Model and Interdisciplinary Application Brownell, Judi; Jameson, Daphne A. (2004-01-01)This article develops a model of problem-based learning (PBL) and shows how PBL has been used for a decade in one graduate management program. PBL capitalizes on synergies among cognitive, affective, and behavioral learning. ...
What is the Impact of Blended Learning Including Micro-Learning on Manager Learning and Behavior Change vs. Impact of Classroom Learning? Avery, Alex (2016-04-01)Today’s learning trends show that with more information and technology available, a globalized workforce, and a changing way we learn, corporate learning particularly manager training needs to meet the following criteria: ...