Search Constraints

Start Over
Filtering by: Creator True, K. Remove constraint Creator: True, K. Committee Member Fern, Xiaoli Remove constraint Committee Member: Fern, Xiaoli

Search Results

  • Information-theoretic Approach to Design and Evaluate Privacy-preserving and Fair Frameworks for Continuous High-dimensional Data

    Creator:
    Alsulaimawi, Zahir Ahmed Hussein
    Abstract:
    Deep learning is becoming the latest trend in sensitive applications, such as healthcare, criminal justice, and finance. As these new applications emerge, adversaries are circumventing them. Further, there have been concerns about the possibility of bias and discrimination in predictive applications. In order to address these issues, we propose an...
    Resource Type:
    Dissertation
    Full Text:
    , and its true risk w.r.t. P is R( f ) , EP(X ,Y )[L( f (x),y)], where L : Y ×Y → R is a given loss

  • Towards Direct Simultaneous Speech Translation

    Creator:
    Chen, Junkun
    Abstract:
    Simultaneous speech translation (SimulST) is widely useful in many cross-lingual communication scenarios, including multinational conferences and international traveling. Since text-based simultaneous machine translation (SimulMT) has achieved great success in recent years. The conventional cascaded approach for SimulST uses a pipeline of streaming ASR followed by simultaneous MT but suffers from...
    Resource Type:
    Dissertation
    Full Text:
    framework. The model can directly translate from the given speech with a wait-k policy guided by a syn

  • A statistical inference framework for finding recurring patterns in large data with applications to energy management

    Creator:
    You, Zeyu
    Abstract:
    We consider the problem of finding unknown patterns that are recurring across multiple sets. For example, finding multiple objects that are present in multiple images or a short DNA code that is repeated across multiple DNA sequences. We first consider a simple problem of finding a single unknown pattern in...
    Resource Type:
    Masters Thesis
    Full Text:
    4.1 Statistical K-pattern Model . . . . . . . . . . . . . . . . . . . . . . . . . . . 24 4.2

  • On surrogate supervision multi-view learning

    Creator:
    Jin, Gaole
    Abstract:
    Data can be represented in multiple views. Traditional multi-view learning methods (i.e., co-training, multi-task learning) focus on improving learning performance using information from the auxiliary view, although information from the target view is sufficient for learning task. However, this work addresses a semi-supervised case of multi-view learning, the surrogate supervision...
    Resource Type:
    Masters Thesis
    Full Text:
    triplets: {(xi, zi, yi)}ni=1, where xi ∈ X , zi ∈ Z, and yi ∈ Y = {1, . . . , K}. However, in surrogate

  • Machine learning for improving the quality of citizen science data

    Creator:
    Yu, Jun
    Abstract:
    Citizen Science is a paradigm in which volunteers from the general public participate in scientific studies, often by performing data collection. This paradigm is especially useful if the scope of the study is too broad to be performed by a limited number of trained scientists. Although citizen scientists can contribute...
    Resource Type:
    Dissertation
    Full Text:
    . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 49 5.4 The average log-likelihood on the holdout data for different values of K in four states. The

  • Creating, Understanding and Applying Machine Learning Models of Multiple Species

    Creator:
    Griffioen, Arwen Twinkle E.
    Abstract:
    Many problems in ecology and conservation biology can be formulated and solved using machine learning algorithms for multi-label classification. This dissertation addresses three topics related to predicting the distributions of multiple species. It improves existing methods and proposes a new modeling paradigm to address the multi-species, multi-label problem. The first...
    Resource Type:
    Dissertation
    Full Text:
    species groups, K

  • Probabilistic models for classification of bioacoustic data

    Creator:
    Lakshminarayanan, Balaji
    Abstract:
    Probabilistic models have been successfully applied for a wide variety of problems, such as but not limited to information retrieval, computer vision, bio-informatics and speech processing. Probabilistic models allow us to encode our assumptions about the data in an elegant fashion and enable us to perform machine learning tasks such...
    Resource Type:
    Masters Thesis
    Full Text:
    0 100 200 300 400 500 600 700 800 900 1000 1100 2 3 4 5 6 7 8 9 10 11 12 Frame index K L

  • Secure Data Analytics under Data Integrity Attacks

    Creator:
    De Silva, Shashini A.
    Abstract:
    There has been tremendous growth in using data analytic and machine learning algorithms to make critical decisions, such as in the national power grid, healthcare operations, and autonomous vehicles. Employing data analytic for decision-making allows cyber attackers to manipulate the decisions of these algorithms through data falsification. Hence, the trustworthiness...
    Resource Type:
    Dissertation
    Full Text:
    of noise. If any x ∈ Σk can be recovered from y, then Φx 6= Φx′ must be true for any pair of

  • Efficient training and feature induction in sequential supervised learning

    Creator:
    Hao, Guohua
    Abstract:
    Sequential supervised learning problems arise in many real applications. This dissertation focuses on two important research directions in sequential supervised learning: efficient training and feature induction. In the direction of efficient training, we study the training of conditional random fields (CRFs), which provide a flexible and powerful model for sequential...
    Resource Type:
    Dissertation
    Full Text:
    ). . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 50 4.2 Fraction of the time that each FAQ feature is true (versus false). Features 1, 3, 4, 7, 8, 10

  • Weak-supervision : Probabilistic Models and Inference

    Creator:
    Pham, Anh
    Abstract:
    In supervised learning, label information can be provided at different levels of granularity. For small datasets, it is possible to acquire a label for each data instance. However, in the big-data regime, this fine granularity approach is prohibitively costly. For example, in semi-supervised learning, only a limited number of samples...
    Resource Type:
    Dissertation
    Full Text:
    instances. ICML, Lille-2015. 3A. T. Pham, Raviv Raich, Xiaoli Z. Fern, W. K. Wong, X. Guan, Discriminative