Search Constraints

Start Over
Filtering by: Committee Member Dietterich, Tom G Remove constraint Committee Member: Dietterich, Tom G

Search Results

  • Towards Narrative Understanding with Deep Neural Networks and Hidden Markov Models

    Creator:
    Orr, J. Walker
    Abstract:
    Narratives are central to communication and the human experience. For a computer system to understand a narrative, it must be able to identify the key facts or plot elements that describe what happened or how the world has changed. These element are called events;establishing a document’s events and the relationships...
    Resource Type:
    Dissertation
    Full Text:
    important correction. I am thankful for Dr. Thomas G. Dietterich and Dr. Alix Gitelman both for their

  • Towards architecture-adaptable parallel programming

    Creator:
    Kumaran, Santhosh
    Abstract:
    There is a software gap in parallel processing. The short lifespan and small installation base of parallel architectures have made it economically infeasible to develop platform-specific parallel programming environments that deliver performance and programmability. One obvious solution is to build architecture-independent programming environments. But the architecture independence usually comes at...
    Resource Type:
    Dissertation
    Full Text:
    four years. I was very fortunate to have Professor Tom Dietterich in my committee. His insightful

  • OGS : a lightweight object-oriented graphics system for instruction

    Creator:
    Zhu, Yanming
    Abstract:
    Existing graphics systems are too large for students to study in an introductory computer graphics course. We have implemented a lightweight, object-oriented graphics system called OGS for instruction. OGS is written in Java. It demonstrates how a graphics system is implemented from scratch and is intended to help students understand...
    Resource Type:
    Capstone Project
    Full Text:
    report . I thank Dr. Timothy Budd and Dr. Tom Dietterich for reading and correcting this report. 35

  • Investigation of automatic construction of reactive controllers

    Creator:
    Westerberg, Caryl J.
    Abstract:
    In real-time control systems, the value of a control decision depends not only on the correctness of the decision but also on the time when that decision is available. Recent work in real-time decision making has used machine learning techniques to automatically construct reactive controllers, that is, controllers with little...
    Resource Type:
    Masters Thesis
    Full Text:
    , advice, and patience. I would also like to thank the members of my committee, Tom Dietterich, and Prasad

  • Parallelism in the SPI algorithm : an investigation

    Creator:
    Fountain, Tony
    Abstract:
    The Symbolic Probabilistic Inference (SPI) algorithm was developed by Bruce D' Ambrosio for efficient calculation of prior probabilities in belief nets [2]. Although the complexity of the SPI algorithm compares favorably with other approaches to probabilistic inference [5], its actual running time is still prohibitively long even for moderately sized...
    Resource Type:
    Capstone Project
    Full Text:
    , Professors Tom Dietterich and Vikram Saletore, for their assistance. I would also like to thank several

  • Learning greedy policies for the easy-first framework

    Creator:
    Xie, Jun
    Abstract:
    Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. This thesis studies the problem of learning...
    Resource Type:
    Masters Thesis
    Full Text:
    my thesis committee: Prof. Thomas G. Dietterich and Prof. Prasad Tadepalli, for their encouragement

  • Constructive induction for improved learning of boolean functions

    Creator:
    Drake, Peter (Peter Dudey), 1970-
    Abstract:
    Supervised learning programs, such as decision tree learners and neural networks, often must learn Boolean functions. The concept being learned may not easily be expressed in terms of the atomic features given. Constructive induction automatically produces higher level features (combinations of the atomic features), which can improve learning performance. The...
    Resource Type:
    Masters Thesis
    Full Text:
    , Tom Dietterich. Thanks also go to Bruce D'ambrosio and Goran Jovanovic, my other committee members

  • Bayesian methods for knowledge transfer and policy search in reinforcement learning

    Creator:
    Wilson, Aaron
    Abstract:
    How can an agent generalize its knowledge to new circumstances? To learn effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
    Resource Type:
    Dissertation
    Full Text:
    pursuer of ideas and inspired me to continue on into graduate level research. Early in my studentship Tom

  • Geographic information systems for coral reef conservation, capacity building, and public education in American Samoa

    Creator:
    Larkin, Emily M.
    Abstract:
    Coral reefs around the world face numerous threats, both natural and anthropogenic, including pollution, natural disasters, invasive species, habitat destruction, and destructive methods of fishing. Given enough time, coral can recover from natural disasters, but anthropogenic threats decrease corals’ ability to recover from things such as hurricanes. It is difficult...
    Resource Type:
    Masters Thesis

  • Learning and Improving Policies for Probabilistic Planning Problems

    Creator:
    Issakkimuthu, Murugeswari
    Abstract:
    In this work, we study the problem of learning and improving policies for probabilistic planning problems. In the first part, we train neural network policies for probabilistic planning problems modeled as factored Markov decision problems. The objective is to train problem-specific neural networks via supervised learning to imitate the action...
    Resource Type:
    Dissertation
    Full Text:
    learning experience I have had as his student, and my Ph.D. committee members, Prof. Thomas Dietterich