Search Constraints

Start Over
Filtering by: Creator Hilliard, Richard F. Remove constraint Creator: Hilliard, Richard F. Committee Member Fern, Alan Remove constraint Committee Member: Fern, Alan

Search Results

  • Toward Automated Decision-Making in Power Systems Wide-Area Protection

    Creator:
    Meier, Richard John
    Abstract:
    In recent years there have been many improvements in the reliability of critical infrastructure systems. Despite these improvements and despite targeted efforts to improve the operation and control of the electric grid, the power systems industry has seen relatively small advances in this regard. For instance, today's power system is...
    Resource Type:
    Masters Thesis
    Full Text:
    Wide-Area Protection AN ABSTRACT OF THE THESIS OF Richard John Meier for the degree of Master of

  • Planning in multi-agent partially observable domains using sparse sampling

    Creator:
    Donneau-Golencer, Thierry D.
    Abstract:
    A large number of sequential decision-making problems in uncertain environments can be modeled as Markov Decision Processes (MDPs). In such settings, an agent can observe at each time step the state of the environment and then executes an action, causing a stochastic transition to a new state of the environment...
    Resource Type:
    Masters Thesis
    Full Text:
    ���<[#†*��+D�<> \�+M�1G<"�+-0/ -`'0�9 ?D��2U?�f<6�^&2D�MO�!�9/ˆD

  • Bayesian optimization with empirical constraints

    Creator:
    Azimi, Javad
    Abstract:
    Bayesian Optimization (BO) methods are often used to optimize an unknown function f(•) that is costly to evaluate. They typically work in an iterative manner. In each iteration, given a set of observation points, BO algorithms select k ≥ 1 points to be evaluated. The results of those points are...
    Resource Type:
    Dissertation
    Full Text:
    (BO) methods are often used to optimize an unknown function f(·) that is costly to evaluate. They

  • Uncertainty in Deep Learning with Implicit Neural Networks

    Creator:
    Ratzlaff, Neale
    Abstract:
    The ability to extract uncertainties from predictions is crucial for the adoption of deep learning systems to safety-critical applications. Uncertainty estimates can be used as a failure signal, which is necessary for automating complex tasks where safety is a concern. Furthermore, current deep learning systems do not provide uncertainty estimates,...
    Resource Type:
    Dissertation
    Full Text:
    is, we consider k-class classification functions f : Rm → Rk parameterized by θ. Consider the joint

  • Principles of Variational Databases

    Creator:
    Ataei, Parisa S.
    Abstract:
    Data variations are prevalent in real-world applications. For example, software vendors have to handle numerous variations in the business requirements, conventions, and environmental settings of a software product. In database-backed software, the database of each version may have a different schema and content. As another example, data scientists often need...
    Resource Type:
    Masters Thesis
    Full Text:
    . A choice f〈e1, e2〉 is labeled by a condition f and resolves to either the al- 7 ternative e1 if

  • Theory and Implementation of a Variational Database Management System

    Creator:
    Ataei, Parisa S.
    Abstract:
    In this thesis, I present the variational database management system, a formal framework and its implementation for representing variation in relational databases and managing variational information needs. A variational database is intended to support any kind of variation in a database. Specific kinds of variation in databases have already been...
    Resource Type:
    Dissertation
    Full Text:
    . A feature f ∈ FeatName can be enabled (i.e., f= true) or disabled (f= false). Features describe

  • Action Segmentation with Limited Supervision

    Creator:
    Li, Jun
    Abstract:
    In this dissertation, we address action segmentation in videos under limited supervision. The goal of action segmentation is to predict an action class for each frame of a video. The limited supervision means ground truth labels of video frames are not available in training. We focus on three types of...
    Resource Type:
    Dissertation
    Full Text:
    error ||KHK − I||F for varying num- bers of iterations in the iterative Cayley transform and the closed

  • Incorporating labeled features into image classification using generalized expectation

    Creator:
    Moore, Travis
    Abstract:
    Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been...
    Resource Type:
    Masters Thesis
    Full Text:
    (A)∑ k=1 λAkfAk(~yA, ~xA)) (3.1) Here Ψ is the set of all factors, f is a feature function for a

  • Efficient Incremental Panorama Reconstruction from Multiple Videos

    Creator:
    Feng, Zhongyuan
    Abstract:
    Constructing a panorama from a set of videos is a long-standing problem in computer vision. A panorama represents an enhanced still-image representation of an entire scene captured in a set of videos, where each video shows only a part of the scene. Importantly, a panorama shows only the scene background,...
    Resource Type:
    Capstone Project
    Full Text:
    Estimation Given an image pair Ii, Ij , as well as matched features f m i ,f n j indexed by m,n respec

  • Parsing with Recurrent Neural Networks

    Creator:
    Cross, James Henry, III
    Abstract:
    Machine learning models for natural language processing have traditionally relied on large numbers of discrete features, built up from atomic categories such as word forms and part-of-speech labels, which are considered completely distinct from each other. Recently however, the advent of dense feature representations coupled with deep learning techniques has...
    Resource Type:
    Dissertation
    Full Text:
    (trained and tested with gold POS tags). . . . . . . . . . . . . . . . . . 47 3.5 Test F-scores for