Search Constraints

Start Over
Filtering by: Advisor Fern, Xiaoli Z. Remove constraint Advisor: Fern, Xiaoli Z. Decade 2010-2019 Remove constraint Decade: 2010-2019

Search Results

  • Learning with Limited Labeled Data in Natural Language Processing

    Creator:
    Obeidat, Rasha
    Abstract:
    The advent of deep learning models leads to a substantial improvement in a wide range of NLP tasks, achieving state-of-art performances without any hand-crafted features. However, training deep models requires a massive amount of labeled data. Labeling new data as a new task or domain emerges consumes time and efforts...
    Resource Type:
    Dissertation
    Full Text:
    : Learning with Limited Labeled Data in Natural Language Processing Abstract approved: Xiaoli Fern The

  • Event detection with forward-backward recurrent neural networks

    Creator:
    Ghaeini, Mohammad Reza
    Abstract:
    Automatic event extraction from natural text is an important and challenging task for natural language understanding. Traditional event detection methods heavily rely on manually engineered rich features. Recent deep learning approaches alleviate this problem by automatic feature engineering. But such efforts, like tradition methods, have so far only focused on...
    Resource Type:
    Masters Thesis
    Full Text:
    Forward-Backward Recurrent Neural Networks Abstract approved: Xiaoli Z. Fern Automatic event extraction

  • Simultaneous segmentation and classification of bird song using CNN

    Creator:
    Narasimhan, Revathy
    Abstract:
    In bioacoustics, automatic animal voice detection and recognition from audio recordings is an emerging topic for animal preservation. Our research focuses on bird bioacoustics, where the goal is to segment bird syllables from the recording and predict the bird species for the syllables. Traditional methods for this task addresses the...
    Resource Type:
    Masters Thesis
    Full Text:
    - lutional encoder-decoder architecture for image segmentation. 2015. [4] Forrest Briggs, Xiaoli Z. Fern

  • Supervised Hierarchical Segmentation for Bird Bioacoustics

    Creator:
    Tjahja, Teresa V.
    Abstract:
    Bioacoustics analysis can be used to conduct environmental monitoring by detecting the presence of birds species. This analysis usually involves identifying the species from their calls. In most frameworks, bird song syllables are extracted from audio recordings and individual syllables are input to a classifier to identify the species. Extraction...
    Resource Type:
    Masters Thesis
    Full Text:
    Abstract approved: Xiaoli Z. Fern Bioacoustics analysis can be used to conduct environmental monitoring

  • Learning greedy policies for the easy-first framework

    Creator:
    Xie, Jun
    Abstract:
    Easy-first, a search-based structured prediction approach, has been applied to many NLP tasks including dependency parsing and coreference resolution. This approach employs a learned greedy policy (action scoring function) to make easy decisions first, which constrains the remaining decisions and makes them easier. This thesis studies the problem of learning...
    Resource Type:
    Masters Thesis
    Full Text:
    the Easy-First Framework Abstract approved: Xiaoli Z. Fern Easy-first, a search-based structured

  • Active learning of constraints for semi-supervised clustering

    Creator:
    Xiong, Sicheng
    Abstract:
    Semi-supervised clustering aims to improve clustering performance by considering user supervision in the form of pairwise constraints. In this paper, we study the active learning problem of selecting pairwise must-link and cannot-link constraints for semisupervised clustering. We consider active learning in an iterative manner where in each iteration queries are...
    Resource Type:
    Masters Thesis
    Full Text:
    Constraints for Semi-Supervised Clustering Abstract approved: Xiaoli Z. Fern Semi-supervised clustering

  • Bayesian optimization with empirical constraints

    Creator:
    Azimi, Javad
    Abstract:
    Bayesian Optimization (BO) methods are often used to optimize an unknown function f(•) that is costly to evaluate. They typically work in an iterative manner. In each iteration, given a set of observation points, BO algorithms select k ≥ 1 points to be evaluated. The results of those points are...
    Resource Type:
    Dissertation
    Full Text:
    : Bayesian Optimization with Empirical Constraints Abstract approved: Xiaoli Z. Fern Bayesian Optimization

  • Detection and Segmentation of Bird Song in Noisy Environments

    Creator:
    Neal, Lawrence W.
    Abstract:
    Recent work in machine learning concerns the detection and identification of bird species from audio recordings of their vocalizations. Such analysis can yield valuable ecological information concerning the activity and distribution of species in the wild. Current species-identification methods require individual syllables of bird audio as input, but field-collected audio...
    Resource Type:
    Honors College Thesis
    Full Text:
    and Segmentation of Bird Song in Noisy Environments Abstract approved: Xiaoli Z. Fern Recent work

  • Open Set Learning with Counterfactual Images

    Creator:
    Neal, Lawrence W.
    Abstract:
    In open set recognition, a classifier must label instances of known classes while detecting instances of unknown classes not encountered during training. To detect unknown classes while still generalizing to new instances of existing classes, this thesis introduces a dataset augmentation technique called counterfactual image generation. This approach, based on...
    Resource Type:
    Masters Thesis
    Full Text:
    Counterfactual Images Abstract approved: Fuxin Li Xiaoli Fern In open set recognition, a classifier must label

  • Learning with Partial Supervision for Clustering and Classification

    Creator:
    Pei, Yuanli
    Abstract:
    In the field of machine learning, clustering and classification are two fundamental tasks. Traditionally, clustering is an unsupervised method, where no supervision about the data is available for learning; classification is a supervised task, where fully-labeled data are collected for training a classifier. In some scenarios, however, we may not...
    Resource Type:
    Dissertation
    Full Text:
    Partial Supervision for Clustering and Classification Abstract approved: Xiaoli Z. Fern In the field of