Search Constraints

Start Over
Filtering by: DOI 10.1186/s12943-015-0288-2 Remove constraint DOI: 10.1186/s12943-015-0288-2 Committee Member Fern, Alan Remove constraint Committee Member: Fern, Alan

Search Results

  • Customizable Visual Traces for Program Explanations

    Creator:
    Bajaj, Divya
    Abstract:
    Correctness and efficiency are important properties of programs. However, to support maintenance and debugging, the programs should also be understandable. Program explanations also play a vital role in educational settings, enhancing the understanding of programs among students. Proof trees provide a sound basis for generating dynamic explanations of programs. But...
    Resource Type:
    Masters Thesis
    Full Text:
    representation, (2) a new variant of the Call-By-Value semantics to generate small traces, and (3) a query

  • 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:
    journey. ”What you seek is seeking you.” — Rumi TABLE OF CONTENTS Page 1 Introduction 1 2 Background

  • Counterfactual States for Atari Agents via Generative Deep Learning

    Creator:
    Olson, Matthew L.
    Abstract:
    Although deep reinforcement learning agents have produced impressive results in many domains, their decision making is difficult to explain to humans. To address this problem, past work has mainly focused on explaining why an action was chosen in a given state. A different type of explanation that is useful is...
    Resource Type:
    Masters Thesis
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2 2 Literature Review 4 2.1 Generative Deep Learning

  • Statistical Properties and Guarantees for Certain Anomaly Detection Relevant Problems

    Creator:
    Liu, Si
    Abstract:
    Anomaly detection aims at detecting the points that appear different than the majority of the data, such that they are suspected to be generated from a different distribution. Anomaly detectors have been applied in many different fields, such as detecting fraudulent behaviors in bank transaction, finding broken sensors in a...
    Resource Type:
    Dissertation
    Full Text:
    1 2 Background 4 2.1 Stopping Rules for iForest . . . . . . . . . . . . . . . . . . . . . . . . 4

  • Collaborative Online Learning For Join Processing

    Creator:
    Xie, Mian
    Abstract:
    Relational binary operators, such as join, are arguably the most costly and frequently used operations in relational data systems. In many join algorithms, the majority of the process time is spent on scanning and attempting to join the parts of the relations that do not satisfy the join condition and...
    Resource Type:
    Capstone Project
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 2 Framework . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.1 Agents

  • Learning to Estimate Multi-Relation Aggregation Functions

    Creator:
    Jadhav, Rashmi Suresh
    Abstract:
    Multi-relation aggregation queries process the join operator before computing the aggregation function. This join is arguably the most costly operation since traditional join algorithms spend majority of their time trying to join the parts of the relations that do not generate any output tuples. This causes slow response times with...
    Resource Type:
    Masters Thesis
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 2 Background . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.1 Nested

  • Agile Bipedal Locomotion via Hierarchical Control by Incorporating Physical Principles, Learning, and Optimization

    Creator:
    Green, Kevin
    Abstract:
    Robotic Bipedal locomotion holds the potential for efficient, robust traversal of difficult terrain. The difficulty lies in the dynamics of locomotion which complicate control and motion planning. Bipedal locomotion dynamics are dimensionally large problems, extremely nonlinear, and operate on the limits of actuator capabilities, which limit the performance of generic...
    Resource Type:
    Dissertation
    Full Text:
    planning tools. We present 1) a ground-up analysis of legged locomotion as a dynamical phenomenon, 2

  • Detecting Anomalies in Object Appearance and Motion Dynamics

    Creator:
    Alotaibi, Mazen
    Abstract:
    Machine common sense remains a broad, potentially unbounded problem in AI. Our focus is to move toward AI systems that can develop common-sense reasoning similar to humans to detect anomalies. In particular, we study the problem of detecting the violation of expectations when object appearance or motion dynamics change from...
    Resource Type:
    Capstone Project
    Full Text:
    naturally with people, and learn from new experiences [1]. A benchmark [2] was created to develop artificial

  • Characterizing and Addressing Dataset Shift with Deep Learning

    Creator:
    Olson, Matthew L.
    Abstract:
    This dissertation delves into understanding, characterizing, and addressing dataset shift in deep learning, a pervasive issue for deployed machine learning systems. Integral aspects of the problem are examined: We start with the use of counterfactual explanations in order to characterize the behavior of deep reinforcement learning agents in visual input...
    Resource Type:
    Dissertation
    Full Text:
    grant #N66001-17-2-4030. Additionally, this work was performed in part under the auspices of the U.S

  • From shape-based object recognition and discovery to 3D scene interpretation

    Creator:
    Payet, Nadia
    Abstract:
    This dissertation addresses a number of inter-related and fundamental problems in computer vision. Specifically, we address object discovery, recognition, segmentation, and 3D pose estimation in images, as well as 3D scene reconstruction and scene interpretation. The key ideas behind our approaches include using shape as a basic object feature, and...
    Resource Type:
    Dissertation
    Full Text:
    Forests (RF) into a unified framework, referred to as (RF)2. We also derive theoretical error bounds of