Search Constraints

Start Over
Filtering by: Creator Fu-Mei Chen Remove constraint Creator: Fu-Mei Chen Degree Field Electrical and Computer Engineering Remove constraint Degree Field: Electrical and Computer Engineering

Search Results

  • Machine Learning for Architectural Design Space Exploration and Resource Control

    Creator:
    Penney, Drew D.
    Abstract:
    Machine learning has enabled significant advancements in diverse fields, yet, with a few exceptions, has had limited impact on computer architecture. Recent work, however, has begun to explore broader application to design, optimization, and simulation. Notably, machine-learning-based strategies often surpass prior state-of-the-art analytical, heuristic, and human-expert approaches. This thesis first...
    Resource Type:
    Masters Thesis
    Full Text:
    Learning for Architectural Design Space Exploration and Resource Control Abstract approved: Lizhong Chen

  • Machine learning for computer architecture design and optimization

    Creator:
    Penney, Drew
    Abstract:
    Machine learning applied to computer architecture has rapidly transitioned from a theoretical novelty to being a driving force behind design, control, and simulation in practically all components. These machine-learning-based methodologies are further notable for their scalability to increasingly complex design challenges, which has allowed these methodologies to surpass the prior...
    Resource Type:
    Dissertation
    Full Text:
    Chen Machine learning applied to computer architecture has rapidly transitioned from a theoretical

  • Towards Deep Learning Model Portability for Domain-Agnostic Device Fingerprinting

    Creator:
    Gaskin, Jared
    Abstract:
    In recent years, RF (Radio Frequency) device fingerprinting using deep learning has emerged as a method of identifying devices solely by their RF transmissions. Conventional approaches to this type of device fingerprinting are not portable to different domains. That is, if a model for this purpose is trained on data...
    Resource Type:
    Masters Thesis
    Full Text:
    : Bechir Hamdaoui Lizhong Chen In recent years, RF (Radio Frequency) device fingerprinting using deep

  • Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms

    Creator:
    Ibrahim, Shahana
    Abstract:
    Crowdsourcing is a popular paradigm to address the high demands for labeled data in big data deluge. It aims to produce accurate labels by effectively integrating noisy, non-expert labeling from crowdsourced workers (annotators). The machine learning community has been studying effective crowdsourcing methods for many years, and many models and...
    Resource Type:
    Masters Thesis
    Full Text:
    : Crowdsourcing via Pairwise Co-occurrences: Identifiability and Algorithms Abstract approved: Xiao Fu

  • Large Scale Tensor Decomposition Algorithms Using Block-randomized Stochastic Proximal Gradient

    Creator:
    Gao, Cheng
    Abstract:
    We consider the problem of computing the cannonical polyadic decomposition (CPD) for large-scale dense tensors. This work is a combination of alternating least squares and fiber sampling. Data sparsity can be leveraged to handle large tensor CPD, but this route is not feasible for dense data. Inspired by stochastic optimization's...
    Resource Type:
    Masters Thesis
    Full Text:
    : Xiao Fu We consider the problem of computing the cannonical polyadic decomposition (CPD) for large

  • Nonlinear neural control with power systems applications

    Creator:
    Chen, Dingguo
    Abstract:
    Extensive studies have been undertaken on the transient stability of large interconnected power systems with flexible ac transmission systems (FACTS) devices installed. Varieties of control methodologies have been proposed to stabilize the postfault system which would otherwise eventually lose stability without a proper control. Generally speaking, regular transient stability is...
    Resource Type:
    Dissertation
    Full Text:
    AN ABSTRACT OF THE THESIS OF Dingguo Chen for the degree of

  • A comparison and assessment of hybrid filter topologies and control algorithms

    Creator:
    Chen, Lijun
    Abstract:
    The harmonic problem in power systems is gaining more attention as incidences correlated with harmonics increase. Conventional passive filtering techniques for harmonic mitigation have inherent problems, and purely active filters have the disadvantages of higher costs and ratings. Hybrid active filters inherit the efficiency of passive filters and the improved...
    Resource Type:
    Masters Thesis
    Full Text:
    control algorithms AN ABSTRACT OF THE THESIS OF Lijun Chen for the degree of Master of Science in

  • Weak-supervision Time-series Analysis

    Creator:
    You, Zeyu
    Abstract:
    Efficient time-series analysis can impact multiple application domains such as motif discovery in gene analysis or music data, extracting spectro-temporal patterns in acoustic scene analysis, or annotating and classifying electrical bio-signals (such as ECG, EEG, and EMG) for medical applications. Time-series analysis involves a variety of tasks. To predict future...
    Resource Type:
    Dissertation
    Full Text:
    : Prof. Xiaoli Fern, Prof. Jinsub Kim, Prof. Xiao Fu, Prof. Sarah Emerson, Prof. Liang Huang and Prof

  • Interlaced instruction window

    Creator:
    Ong, Wee-Shong
    Abstract:
    A relatively recent development in the late 1980s in processors has been the superscalar processor. Superscalar processors use multiple pipelines in an attempt to achieve higher performance than previous generations of processors. Having multiple pipelines makes it possible to execute more than one instruction per cycle. However, since instructions are...
    Resource Type:
    Masters Thesis
    Full Text:
    Lee, my minor professor, Dr. John Chen, the Graduate Council Representative and Dr. cetin Koc for

  • Cost-Age-Time Data Organized Garbage Collection

    Creator:
    Lee, Dongjun
    Abstract:
    NAND flash based solid state drives (SSDs) require out-of-place updating due to the characteristics of flash memories. In addition, due to the mismatched granularity between read/write and erase operations, a cleaning policy involving garbage collection and wear leveling has to perform data migration incurring high overhead. Another challenge is that...
    Resource Type:
    Masters Thesis