Search Constraints

Start Over
Filtering by: Creator Edgington, Aaron James Remove constraint Creator: Edgington, Aaron James Academic Affiliation Electrical Engineering and Computer Science Remove constraint Academic Affiliation: Electrical Engineering and Computer Science Non-Academic Affiliation Oregon State University. Graduate School Remove constraint Non-Academic Affiliation: Oregon State University. Graduate School

Search Results

  • Bayesian methods for knowledge transfer and policy search in reinforcement learning

    Creator:
    Wilson, Aaron
    Abstract:
    How can an agent generalize its knowledge to new circumstances? To learn effectively an agent acting in a sequential decision problem must make intelligent action selection choices based on its available knowledge. This dissertation focuses on Bayesian methods of representing learned knowledge and develops novel algorithms that exploit the represented...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE DISSERTATION OF Aaron Wilson for the

  • The Pursuit of Hoppiness : Propelling Hop into the Genomic Era

    Creator:
    Hill, Steven T.
    Abstract:
    Hop (Humulus lupulus L. var lupulus) is a plant of great cultural significance, used as a medicinal herb for thousands of years, and for flavor and as a preservative in brewing beer. Studies of the medicinal effects of the unique compounds produced by hop have led to interest from the...
    Resource Type:
    Masters Thesis
    Full Text:
    . CONTRIBUTION OF AUTHORS Dr. Aaron Liston provided expert background knowledge and contributed to writing

  • Painterly rendering using space-time varying style parameters

    Creator:
    Kagaya, Mizuki
    Abstract:
    Automatic painterly rendering systems have been proposed but they opted for selecting a single style to generate paintings from images, which lacks the ability of creatively using multiple styles to focus important objects and deemphasize unimportant part of the scenes. We provide a multi-style painting framework to address this issue...
    Resource Type:
    Masters Thesis
    Full Text:
    , AARON, which is capable of drawing human figures and plants [7]. Winkenbach introduced an automatic pen

  • Relational Networks for Visual Relationship Detection in Images

    Creator:
    Nguyen, Khoi
    Abstract:
    This thesis is about visual relationship detection. This is an important task in computer vision. The goal is to detect all visual relationships in a given image between objects. This thesis presents a new approach to this problem. Our approach does not use an object detector as a common pre-processing...
    Resource Type:
    Masters Thesis
    Full Text:
    ] Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Dollár, and

  • Quantum dots-fullerene based molecular beacons for highly sensitive DNA detection

    Creator:
    Liu, Ye
    Abstract:
    We demonstrated a low-cost and high-sensitivity DNA detection method using quantum dot-fullerene based molecular beacons (MBs) and magnetic nanoparticles. The MB tethered magnetic nanoparticles can be well dispersed in analytes for efficient DNA capture and concentrated by an external magnetic field for enhanced fluorescence signal detection. The detection requires only...
    Resource Type:
    Masters Thesis

  • Toward computer vision for understanding American football in video

    Creator:
    Hess, Robin W.
    Abstract:
    In this work, I examine the problem of understanding American football in video. In particular, I present several mid-level computer vision algorithms that each accomplish a different sub-task within a larger system for annotating, interpreting, and analyzing collections of American football video. The analysis of football video is useful in...
    Resource Type:
    Dissertation
    Full Text:
    that greatly. Thanks es- pecially to Aaron Wilson, Aswin Raghavan, Avneet Sandhu, Chandan Sarkar

  • High-Dimensional Reinforcement Learning with Human Feedback

    Creator:
    Curran, William
    Abstract:
    State-of-the-art personal robots need to perform complex manipulation tasks to be viable in complex scenarios. However, many of these robots, like the PR2, use manipulators with high degrees of freedom. High degrees of freedom are desirable from a functionality standpoint, but make the learning task more difficult by adding a...
    Resource Type:
    Dissertation

  • Learning affinities of exemplar videos for multi-view action recognition

    Creator:
    Roy, Anirban
    Abstract:
    This thesis addresses a fundamental computer vision problem, that of action recognition. The goal of action recognition is to recognize a class of human actions in a given video. Action recognition has a wide range of applications, including automated surveillance, sports video analysis, internet-based searches etc. The main challenge is...
    Resource Type:
    Masters Thesis

  • Design techniques for clocking high performance signaling systems

    Creator:
    Hanumolu, Pavan Kumar
    Abstract:
    Scaling of CMOS technology has progressed relentlessly for the past several decades. In order for this unprecedented scaling to benefit the performance of large digital systems, the communication bandwidth between integrated circuits (ICs) must scale accordingly. However, interconnect technology does not scale as aggressively, making communication between chips the major...
    Resource Type:
    Dissertation
    Full Text:
    Balamurugan, Bryan Casper, David Johnson, James Jaussi, Joe Kennedy, Mozghan Mansuri, Aaron Martin, and Frank

  • Gender differences in robot teleoperation

    Creator:
    Showkat, Dilruba
    Abstract:
    Gender issues have recently received increased attention in human robot interaction (HRI). Because robots are becoming part of our homes and daily lives, it is important to understand how different groups of people use them. To the best of our knowledge, almost no research has been done that investigates gender...
    Resource Type:
    Masters Thesis