Shared more. Cited more. Safe forever.
    • advanced search
    • submit works
    • about
    • help
    • contact us
    • login
    View Item 
    •   MOspace Home
    • University of Missouri-Kansas City
    • School of Graduate Studies (UMKC)
    • Theses and Dissertations (UMKC)
    • Theses (UMKC)
    • 2020 Theses (UMKC)
    • 2020 UMKC Theses - Freely Available Online
    • View Item
    •   MOspace Home
    • University of Missouri-Kansas City
    • School of Graduate Studies (UMKC)
    • Theses and Dissertations (UMKC)
    • Theses (UMKC)
    • 2020 Theses (UMKC)
    • 2020 UMKC Theses - Freely Available Online
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.
    advanced searchsubmit worksabouthelpcontact us

    Browse

    All of MOspaceCommunities & CollectionsDate IssuedAuthor/ContributorTitleIdentifierThesis DepartmentThesis AdvisorThesis SemesterThis CollectionDate IssuedAuthor/ContributorTitleIdentifierThesis DepartmentThesis AdvisorThesis Semester

    Statistics

    Most Popular ItemsStatistics by CountryMost Popular AuthorsStatistics by Referrer

    DeepSampling: Image Sampling Technique for Cost-Effective Deep Learning

    Gaikwad, Priyanka V.
    View/Open
    [PDF] DeepSampling: Image Sampling Technique for Cost-Effective Deep Learning (1.780Mb)
    Date
    2020
    Metadata
    [+] Show full item record
    Abstract
    Deep learning is beneficial from big data while facing computationally expensive, with an increase in data size. Some severe data issues, such as the presence of highly skewed, sparse, and imbalanced data, would substantially influence the findings of machine learning. Due to the complexity of such data, the ability to assess and evaluate the data is central to cost-effective deep learning. More specifically, in Deep Learning, choosing the right validation method is vital to ensure the accuracy and biases of the validation process. Current validation techniques, including k-fold cross-validation or random split of training and testing datasets, are hampered by the lack of systematic sampling with a comprehensive understanding of the data. In this thesis, we proposed a sampling technique called DeepSampling that aims at achieving cost-effective deep learning for a given application. For the proposed DeepSampling framework, two sampling schemes are designed [1] to resolve the imbalanced data issues using Generative Adversarial Networks (GANs), [2] to develop an effective sampling technique based on clustering. The clustering techniques are based on Mahalanobis distance metric and use t-SNE (T-distributed Stochastic Neighbor Embedding), to overcome the data skewness and sparseness issues. The proposed DeepSampling technique for cost-effective deep learning has been evaluated with three Deep Learning models and four benchmark datasets, including MNIST, Breast Histology, Malaria cell images, and Stanford dog. The results confirm that the accuracies obtained by DeepSampling are improved by approximately 2-3% for image classification, compared to traditional evaluation techniques on the same dataset.
    Table of Contents
    Introduction -- Background and related work -- Proposed framework -- Results and evaluations -- Conclusion and future work
    URI
    https://hdl.handle.net/10355/74350
    Degree
    M.S. (Master of Science)
    Thesis Department
    Computer Science (UMKC)
    Collections
    • 2020 UMKC Theses - Freely Available Online
    • Computer Science and Electrical Engineering Electronic Theses and Dissertations (UMKC)

    If you encounter harmful or offensive content or language on this site please email us at harmfulcontent@umkc.edu. To learn more read our Harmful Content in Library and Archives Collections Policy.

    Send Feedback
    hosted by University of Missouri Library Systems
     

     


    If you encounter harmful or offensive content or language on this site please email us at harmfulcontent@umkc.edu. To learn more read our Harmful Content in Library and Archives Collections Policy.

    Send Feedback
    hosted by University of Missouri Library Systems