Search Constraints

Start Over
Filtering by: Creator Hosack, Geoffrey R. Remove constraint Creator: Hosack, Geoffrey R. Committee Member Li, Fuxin Remove constraint Committee Member: Li, Fuxin

Search Results

  • Augmented Deep Learning Techniques for Robotic State Estimation

    Creator:
    Nicolai, Austin L.
    Abstract:
    While robotic systems may have once been relegated to structured environments and automation style tasks, in recent years these boundaries have begun to erode. As robots begin to operate in largely unstructured environments, it becomes more difficult for them to effectively interpret their surroundings. As sensor technology improves, the amount...
    Resource Type:
    Dissertation
    Full Text:
    Deep Learning Techniques for Robotic State Estimation Abstract approved: Geoffrey A. Hollinger While

  • Robots Against Infectious Diseases : A Technologically Grounded, Human-Centered Exploration

    Creator:
    Kraft, Kory
    Abstract:
    Robots have the potential to protect health care workers, provide patient care, and ultimately save lives in infectious disease outbreaks. Nevertheless, infectious disease outbreak scenarios present unique technological and social challenges for robotics. This work explores what robots can and should do in the fight against infectious diseases. We present...
    Resource Type:
    Masters Thesis

  • Topological Learning for Robotic Exploration and Navigation in Uncertain Environments

    Creator:
    Saroya, Manish R.
    Abstract:
    The effectiveness of robot autonomy is governed by the ability to make decisions based on online sensor measurements and a prior belief of the environment. Uncertainty in the environment introduces challenges to robotic decision making. This thesis address two key robot decision making problems: exploration and navigation. The robotic exploration...
    Resource Type:
    Masters Thesis
    Full Text:
    AN ABSTRACT OF THE THESIS OF Manish R. Saroya for the

  • Pixel- and Frame-level Video Labeling using Spatial and Temporal Convolutional Networks

    Creator:
    Lei, Peng
    Abstract:
    This dissertation addresses the problem of video labeling at both the frame and pixel levels using deep learning. For pixel-level video labeling, we have studied two problems: i) Spatiotemporal video segmentation and ii) Boundary detection and boundary flow estimation. For the problem of spatiotemporal video segmentation, we have developed recurrent...
    Resource Type:
    Dissertation
    Full Text:
    takes previous RTDF predictions yr

  • Window Axial Vision Transformer for Image Classification

    Creator:
    Lee, Jisoo
    Abstract:
    Currently, a popular approach to image classification uses the deep Transformer architecture. In a Transformer, the attention mechanism enables the model to learn efficiently with fewer computational resources than the convolutional neural networks (CNNs). In this thesis, we study the sparse attention mechanism widely used in the Transformers developed specifically...
    Resource Type:
    Masters Thesis
    Full Text:
    [1] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel

  • Graph Imitation Learning for Optimal Joint Beamforming and Antenna Selection

    Creator:
    Shrestha, Sagar
    Abstract:
    Transmit beamforming is an important technique employed to improve efficiency and signal quality in wireless communication systems by steering signals towards their in- tended users. It often arises jointly with the antenna selection problem due to various reasons, such as limited number of radio frequency (RF) chains and energy/resource effi-...
    Resource Type:
    Masters Thesis
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . 7 2.2 Robust Beamforming and SDR . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.3 Joint (R

  • Image Based Crypto

    Creator:
    Basa, Gungor
    Abstract:
    The ability to create reproducible cryptographically secure keys from temporal environments (e.g., images) has the potential to be a contributor to effective cryptographic mechanisms. Due to the noisy nature of these environments, achieving this goal in a user friendly fashion is a very challenging task, especially since there exists a...
    Resource Type:
    Masters Thesis
    Full Text:
    secret respectively. q and p be primes and q, r are co prime to each other such that |q| = κ, |r| = `, p

  • An analysis of training methodologies for deep visual trackers

    Creator:
    Fiez, Trevor
    Abstract:
    This thesis considers the problem of training convolutional neural networks for online visual tracking. A major challenge for single object visual tracking is that most training sets with frame-level track annotations are quite small, due to the prohibitive cost of manual annotation. Current training approaches either supplement the annotations with...
    Resource Type:
    Masters Thesis

  • Fine-Grained Object Recognition Under Limited Training Data

    Creator:
    Lam, Michael Q.
    Abstract:
    This dissertation addresses object recognition in challenging settings, where distinct object classes are visually very similar (e.g., species of birds and insects) and/or access to training examples of object classes is limited (e.g., due to the associated high costs of data annotation). In this dissertation, we present a variety of...
    Resource Type:
    Dissertation
    Full Text:
    7→ℜ to guide the search towards high-quality outputs; and Cost function C : X×Y 7→ℜ to score the

  • Investigating Latent State and Uncertainty Representations in Reinforcement Learning

    Creator:
    Koul, Anurag
    Abstract:
    Learning latent space representations of high-dimensional world states has been at the core of recent rapid growth in reinforcement learning(RL). At the same time, RL algo- rithms have suffered from ignored uncertainties in the predicted estimates of model-free or model-based methods. In our work, we investigate both of these aspects...
    Resource Type:
    Dissertation
    Full Text:
    QBN’s to quantize memory and observations. (3.) Insertion and Fine Tuning. The modules labeled O, R are