Search Constraints

Start Over
Filtering by: Creator Tait, Cynthia K. Remove constraint Creator: Tait, Cynthia K. Degree Field Computer Science Remove constraint Degree Field: Computer Science

Search Results

  • Toward Disentangling the Activations of the Deep Networks via Low-dimensional Embedding and Non-negative Factorization

    Creator:
    Khorram, Saeed
    Abstract:
    In this thesis, we introduce a novel Explanation Neural Network (XNN) to explain the predictions made by a deep network. The XNN works by embedding a high-dimensional activation vector of a deep network layer non-linearly into a low-dimensional explanation space while retaining faithfulness i.e., the original deep learning predictions can...
    Resource Type:
    Masters Thesis
    Full Text:
    feature is viEi, the product of the weight of the x-feature in the approxi- mation of ŷ(k) timed by the

  • 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:
    subqueries. The join operation is 20 Operators: • := < | ≤ | = | 6= | > | ≥ ◦ := ∪ | ∩ Constant: k

  • The InclusiveMag Method: A Start Towards More Inclusive Software for Diverse Populations

    Creator:
    Mendez, Christopher
    Abstract:
    How can software practitioners assess whether their software supports diverse users? Although there are empirical processes that can be used to find “inclusivity bugs” piecemeal, what is often needed is a systematic inspection method to assess software’s support for diverse populations. To help fill this gap, this thesis introduces InclusiveMag,...
    Resource Type:
    Masters Thesis

  • Semantic embodied navigation : developing agents that navigate from language and vision

    Creator:
    Krantz, Jacob
    Abstract:
    Autonomous robotic agents are on their way to becoming in-home personal assistants, construction assistants, and warehouse workers. The degree of autonomy of such systems is reflected by the manner in which we specify goals to them; the abstraction of low-level commands to high-level goals goes hand-in-hand with increased autonomy. In...
    Resource Type:
    Dissertation

  • Reasons Behind the Low Enrollment of Women in Computer Science

    Creator:
    Schneider, Ashley R.
    Abstract:
    Over the past few decades, the ratio of women to men in many traditionally maledominated fields has become much more equal. However, in science, technology, engineering, and math (STEM) fields the ratio has not improved at the same rate. In computer science the ratio is still very uneven. Today women...
    Resource Type:
    Honors College Thesis
    Full Text:
    females than the males. Thomas Zimmerman from IBM Research, David Johnson, Cynthia Wambsgans from the

  • Random access machine in secure multi-party computation

    Creator:
    Hu, Zhangxiang
    Abstract:
    Secure multi-party computation (MPC) is a conceptual framework in cryptography. It allows distrusting parties engage in a protocol to perform a computational task while still maintain some secure properties. Most existing approaches are required to interpret functions as a boolean circuit. With the recent state-of-art circuit garbling scheme, the performance...
    Resource Type:
    Masters Thesis
    Full Text:
    protocol, A be an adversary, and Z be an environment, we define EXEC(F , π, A, Z, k) to be the random

  • Poisoning machine learning models to increase membership inference risks

    Creator:
    Le, Hoang
    Abstract:
    Deep learning is now being utilized widely in applications where sensitive data is being used for model training, for example, in health care. In this scenario, any data leakage will cause privacy concerns to whose data records are used to train the model. An attacker can actively cause privacy leakage...
    Resource Type:
    Masters Thesis
    Full Text:
    Conference on Machine Learning, pages 1596–1606. PMLR, 2019. [8] Cynthia Dwork, Aaron Roth, et al. The

  • New Approaches to Depth-Based Render Techniques Using Pixel Synchronization

    Creator:
    Pawlowski, Bryan
    Abstract:
    As the nonstop advancement of graphics hardware continues, new features are being added to the graphics pipeline on a regular basis. One of these advancements is called Pixel Synchronization, which allows a graphics programmer more power with certain types of data structures that may be accessed by multiple shader units...
    Resource Type:
    Masters Thesis
    Full Text:
    thank my family, my Mother, Clara, my father, Stephen, Cynthia, Danny, Robert and Laurel. Thanks to my

  • Multiple Instance Multiple Label Learning with Limited Supervision

    Creator:
    Nguyen, Tam
    Abstract:
    In weak supervision learning, label information can be provided at different levels of granularity. For example, in multi-instance multi-label learning, samples are organized into bags and labels for each class are provided at the bag level. For small datasets, this approach offers means of reducing the labeling efforts. However, in...
    Resource Type:
    Dissertation
    Full Text:
    - rithms evaluated on 11 datasets (a)-(k). . . . . . . . . . . . . . . . . . . . 70 3.8 Instance accuracy

  • Mental Models of Mere Mortals with Explanations of Reinforcement Learning

    Creator:
    Anderson, Andrew A.
    Abstract:
    How should reinforcement learning (RL) agents explain themselves to humans not trained in AI? To gain insights into this question, we conducted a 124 participant, four-treatment experiment to compare participants’ mental models of an RL agent in the context of a simple Real-Time Strategy (RTS) game. The four treatments isolated...
    Resource Type:
    Masters Thesis