Search Constraints

Start Over
Filtering by: Creator Watkins, Deane A. Remove constraint Creator: Watkins, Deane A. Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad

Search Results

  • Learning with Limited Labeled Data in Natural Language Processing

    Creator:
    Obeidat, Rasha
    Abstract:
    The advent of deep learning models leads to a substantial improvement in a wide range of NLP tasks, achieving state-of-art performances without any hand-crafted features. However, training deep models requires a massive amount of labeled data. Labeling new data as a new task or domain emerges consumes time and efforts...
    Resource Type:
    Dissertation
    Full Text:
    advent of deep learning models leads to a substantial improvement in a wide range of NLP tasks

  • 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:
    and combina- torial circuitry to implement a game playing penguin in Pengi [AC87]. Then, Watkins

  • Microstructure of radiation damage in the uranium film and its backing materials irradiated with 136 MeV 136Xe+26, Microstructure of radiation damage in the uranium film and its backing materials irradiated with 136 MeV ¹³⁶Xe⁺²⁶

    Creator:
    Sadi, Supriyadi
    Abstract:
    Microstructure changes in uranium and uranium/metal alloys due to radiation damage are of great interest in nuclear science and engineering. Titanium has attracted attention because of its similarity to Zr. It has been proposed for use in the second generation of fusion reactors due to its resistance to radiation-induced swelling....
    Resource Type:
    Dissertation
    Full Text:
    radiation-induced swelling. Aluminum can be regarded as a standard absorbing material or backing

  • Reinforcement learning for job-shop scheduling

    Creator:
    Zhang, Wei, 1960-
    Resource Type:
    Dissertation
    Full Text:
    , Jaakkola et al., 1994, Sutton, 1988, Tsitsiklis, 1994, Watkins and Dayan, 1992] makes them attractive as a

  • Adaptive Multiagent Traffic Management for Autonomous Robotic Systems

    Creator:
    Rebhuhn, Carrie
    Abstract:
    There is growing commercial interest in the use of unmanned aerial vehicles (UAVs) in urban environments, specifically for package delivery applications. However, the size, complexity and sheer numbers of expected UAVs makes conventional air traffic management that relies on human air traffic controllers infeasible. To enable UAVs to safely and...
    Resource Type:
    Dissertation
    Full Text:
    environments, it is essential to develop autonomous UAV management strategies. We introduce a dynamic

  • Evaluation functions in aerial image segmentation

    Creator:
    Langford, William T.
    Abstract:
    Remote sensing is the most practical way to acquire large amounts of land cover data for monitoring and understanding environmental change, so it is important to be able to map land cover from imagery. Maps defining land cover patches as polygons rather than pixels greatly improve processing efficiency in models...
    Resource Type:
    Dissertation
    Full Text:
    segmentation. Assigning a cover type label to a pixel or polygon is called classiflcation. Accuracy of maps

  • Deep Learning for Human and Biological Languages

    Creator:
    Hong, Junki
    Abstract:
    We explore the application of deep learning to the disparate fields of natural language processing and computational biology. Both the sentences uttered by humans as well as the RNA and protein sequences found within the cells of their bodies can be considered formal languages in computer science, as sets of...
    Resource Type:
    Dissertation
    Full Text:
    language sentences have a large number of types but a limited sequence of tokens, while nucleotides in

  • An Information Modeling Framework for Support of Sustainable Manufacturing System Design Decision Making

    Creator:
    Shankar Raman, Arvind
    Abstract:
    Manufacturing technology has continuously evolved and advanced over the past century; this has led to an increase in the production of consumer and industrial goods driven by simultaneous growth in population and wealth. Despite the resulting economic and labor growth, environmental impacts of manufacturing have increased dramatically due to the...
    Resource Type:
    Dissertation
    Full Text:
    (sustainability performance information) remains a barrier to operational decision-making. Existing assessment

  • Reinforcement learning-based off-equilibrium incentives to approximate the VCG mechanism

    Creator:
    Moissinac, Béatrice
    Abstract:
    Auctions are used to solve resource allocation problem between many agents and many items in real-world settings. Unfortunately, in most cases, it is possible for selfish agents to manipulate the system for their own interest at the expense of the social welfare. Such manipulation can be prevented using the Vickrey-Clarke-Groves...
    Resource Type:
    Masters Thesis
    Full Text:
    desirable outcomes in a congestion game. c©Copyright by Béatrice Moissinac November 22, 2013 All Rights

  • Model-based approximation methods for reinforcement learning

    Creator:
    Wang, Xin
    Abstract:
    The thesis focuses on model-based approximation methods for reinforcement learning with large scale applications such as combinatorial optimization problems. First, the thesis proposes two new model-based methods to stablize the value–function approximation for reinforcement learning. The first one is the BFBP algorithm, a batch-like reinforcement learning process which iterates between...
    Resource Type:
    Dissertation
    Full Text:
    value–function approximation for reinforcement learning. The first one is the BFBP algorithm, a batch