T
Thomas G. Dietterich
Researcher at Oregon State University
Publications - 286
Citations - 58937
Thomas G. Dietterich is an academic researcher from Oregon State University. The author has contributed to research in topics: Reinforcement learning & Markov decision process. The author has an hindex of 74, co-authored 279 publications receiving 51935 citations. Previous affiliations of Thomas G. Dietterich include University of Wyoming & Stanford University.
Papers
More filters
Book ChapterDOI
A comparative study of ID3 and backpropagation for English text-to-speech mapping
TL;DR: The performance of the error backpropagation (BP) and ID3 learning algorithms was compared on the task of mapping English text to phonemes and stresses and it was shown that BP consistently out-performs ID3 on this task by several percentage points.
Proceedings Article
Learning probabilistic behavior models in real-time strategy games
Ethan W. Dereszynski,Jesse Hostetler,Alan Fern,Thomas G. Dietterich,Thao-Trang Hoang,Mark Udarbe +5 more
TL;DR: The behavior model is based on the well-developed and generic paradigm of hidden Markov models, which supports a variety of uses for the design of AI players and human assistants and provides both a qualitative and quantitative assessment of the learned model's utility.
Proceedings Article
Learnability of the Superset Label Learning Problem
Li-Ping Liu,Thomas G. Dietterich +1 more
TL;DR: Empirical Risk Minimizing learners that use the superset error as the empirical risk measure are analyzed and the conditions for ERM learnability and sample complexity for the realizable case are given.
Proceedings ArticleDOI
Learning non-redundant codebooks for classifying complex objects
TL;DR: A simple yet effective framework for learning multiple non-redundant codebooks to extract discriminative information that was not captured by preceding codebooks and their corresponding classifiers is described.
Proceedings Article
Low bias bagged support vector machines
TL;DR: Experiments indicate that bagging of low-bias SVMs (the "lobag" algorithm) never hurts generalization performance and often improves it compared with well-tuned single SVMs and to bags of individually well- Tuned SVMs.