Search Constraints

Start Over
Filtering by: Creator Melvin, Edward F. Remove constraint Creator: Melvin, Edward F. Committee Member Fern, Alan Remove constraint Committee Member: Fern, Alan

Search Results

  • 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

  • Applying hierarchical and adaptive control to coordinating simple robots

    Creator:
    Knudson, Matthew D.
    Abstract:
    Coordinating multiple robots to achieve a complex task requires solving two distinct control problems: the high-level control problem of ensuring that each robot aims to perform a useful task (e.g., coordination) and the low-level control problem of ensuring that each robot actually performs the correct actions to achieve its task...
    Resource Type:
    Masters Thesis
    Full Text:
    speed (given by a linear function F (Q)). 22 4.2 Probabilistic Output: A demonstration of the path

  • 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

  • Decentralized Multi-Robot Exploration with Sparse Communication through Deep Imitation Learning

    Creator:
    Senewiratne, Yomal K.
    Abstract:
    We present a method for decentralized, multi-robot exploration in adverse environments where communication is minimal. A key conceptual feature of our method is enabling implicit coordination between robots by training a Convolutional Neural Network (CNN) as a heuristic for planning using Monte Carlo Tree Search (MCTS). Our method consists of...
    Resource Type:
    Masters Thesis
    Full Text:
    vertices as possible. Thus, the reward f(p) is defined as the number of occupied vertices that are

  • Agile Bipedal Maneuvers Optimized then Learned from Single Rigid-Body Model Dynamics

    Creator:
    Batke, Ryan
    Abstract:
    As bipedal robots move ever closer to being integrated into all manner of real world envi-ronments there is a necessity to push their dynamic capabilities to meet or exceed those of humans and animals. Advancements must be made to address ordinary challenges that arise everyday in the same environments that...
    Resource Type:
    Masters Thesis
    Full Text:
    model has been adopted as a 5 CoM F Figure 2.1: Sketch of a Linear Inverted Pendulum model

  • 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

  • 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:
    for this round 6: Grow additional Tm � Tm�1 trees 7: Let F stand for the forest of all the Tm trees

  • Generative Models Meet Explainable AI and Long-Tail Learning: from Attribution Maps to Image Synthesis

    Creator:
    Khorram, Saeed
    Abstract:
    The advancement of artificial intelligence (AI) has led to transformative developments across multiple sectors, fostering innovation and redefining our interactions with technology. As AI matures and becomes integrated into society, it offers numerous opportunities to address global challenges and revolutionize a wide array of human endeavors. These advances are driven...
    Resource Type:
    Dissertation
    Full Text:
    the loss functions are outlined via dashed lines. The classifier f and discriminator D are only used

  • 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:
    optimization problem of the form, minimize x,z f(x) + g(z) (2.3) subject to Ax+Bz = c ADMM, firstly, forms

  • Structured learning with latent variables : theory and algorithms

    Creator:
    Zhao, Kai
    Abstract:
    Most tasks in natural language processing (NLP) try to map structured input (e.g., sentence or word sequence) to some form of structured output (tag sequence, parse tree, semantic graph, translated/paraphrased/compressed sentence), a problem known as “structured prediction”. While various learning algorithms such as the perceptron, maximum entropy, and expectation-maximization have...
    Resource Type:
    Dissertation
    Full Text:
    function F : X × Y → R: y∗ = argmax y∈Y(x) F (x, y). (2.1) Usually the scoring function F (·, ·) is