Search Constraints

Start Over
Filtering by: Creator Lord-Castillo, Brett K. Remove constraint Creator: Lord-Castillo, Brett K. Committee Member Tyler, Brett Remove constraint Committee Member: Tyler, Brett

Search Results

  • Incorporating labeled features into image classification using generalized expectation

    Creator:
    Moore, Travis
    Abstract:
    Image classification is a difficult problem, often requiring large training sets to get satisfactory results. However this is a task that humans perform very well, and incorporating user feedback into these learning algorithms could help reduce the dependency on large amounts of labeled training data. This process has already been...
    Resource Type:
    Masters Thesis
    Full Text:
    exponent of a weighted sum of features over a subset of ~X and ~Y . P (~Y | ~X) = 1 Z( ~X) ∏ A∈Ψ exp( K

  • Leveraging Structures of the Data in Deep Learning

    Creator:
    Li, Xingyi
    Abstract:
    The performance of deep learning frameworks could be significantly improved through considering the particular underlying structures for each dataset. In this thesis, I summarize our three work about boosting the performance of deep learning models through leveraging structures of the data. In the first work, we theoretically justify that, for...
    Resource Type:
    Dissertation
    Full Text:
    , Dr. Prasad Tadepalli, and Dr. Brett Tyler. Thank you for your time and discussions during any exams

  • Bi-criteria Scheduling in an Assembly Flow Shop with Limited Buffer Storage and Shift Production

    Creator:
    Aryal, Ayush R.
    Abstract:
    In this research, the comparative performance of permutation and non-permutation schedules is investigated in an assembly flow shop (AFS) with shift production, where a limited buffer storage is available between two machines. Most of the traditional scheduling problems consider continuous production, i.e., production occurs for 24 hours (3 * 8-hour...
    Resource Type:
    Masters Thesis
    Full Text:
    , my minor professor, Dr. Hector Vergara, my committee member, and Dr. Brett Tyler, my graduate

  • 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:
    ) = || ∫ Z k(z, ·)dDZ(z)− ∫ Z k(z, ·)dEZ(z)||Hk (3.5) and Hk is a reproducing kernel Hilbert space, and an

  • Advances in Simultaneous Translation

    Creator:
    Zheng, Renjie
    Abstract:
    Simultaneous translation, which translates concurrently with the source language speech, is widely used in many scenarios including multilateral organizations. However, it is well known to be one of the most challenging tasks for humans due to the simultaneous perception and production in two languages. On the other hand, simultaneous translation...
    Resource Type:
    Dissertation
    Full Text:
    . Lizhong Chen, Prof. Brett Tyler and Prof. Alan Fern, for their insightful comments and encouragement, but

  • Three Sites are Better than One : Exploring Multivalency in LC8 Binding Partners

    Creator:
    Clark, Sarah A.
    Abstract:
    Hub proteins bind a large number of partners to facilitate structural changes and downstream protein interactions. LC8, a highly conserved protein homodimer, is a unique hub that regulates the activity of proteins in a wide range of cellular processes by binding to intrinsically disordered regions. With many of these systems,...
    Resource Type:
    Dissertation

  • Exploring Protein Structure: Seeing the Forest and the Trees

    Creator:
    Brereton, Andrew E.
    Abstract:
    Life on Earth intimately depends on the function of countless proteins. For the majority of studied proteins, function absolutely depends on conformation (i.e. 3-dimensional shape in solution). The exact nature of how a protein goes from an unfolded linear polypeptide chain to an organized folded molecule is still not known,...
    Resource Type:
    Dissertation

  • Robust and Efficient Classification of Videos in the Wild

    Creator:
    Mahasseni, Behrooz
    Abstract:
    Recognizing human actions in videos is a long-standing problem in computer vision with a wide range of applications including video surveillance, content retrieval, and sports analysis. This thesis focuses on addressing efficiency and robustness of video classification in unconstrained real-world settings. The thesis work can be broadly divided into four...
    Resource Type:
    Dissertation
    Full Text:
    deformable parts model (DPM) [33]. DPM has K nodes representing K action parts, connected in a star

  • Computational Approaches for Understanding Combinatorial Gene Regulation

    Creator:
    Ansariola, Mitra
    Abstract:
    Gene regulation is a complex mechanism that controls the spatial and temporal expression of genes in a living cell. My dissertation studies focus on two problems. First, tissue-specific gene expression prediction from DNA sequence and chromatin state, and second, the accurate discovery of small over-represented regulatory circuits in gene regulatory...
    Resource Type:
    Dissertation
    Full Text:
    aspects of my projects. I thank my Ph.D. committee member Dr. Brett Tyler, previous teachers and mentors

  • Machine Learning Methods for the Discovery and Analysis of MicroRNAs

    Creator:
    Bell, Jimmy D.
    Abstract:
    MicroRNAs are a highly conserved class of small endogenous RNA, about ~22nt in length, involved in post-transcriptional gene silencing and have prominent roles in disease and development. Though the process of microRNA discovery was once an arduous task, the advent of high throughput sequencing technology has resulted in novel microRNAs...
    Resource Type:
    Masters Thesis