Search Constraints

Start Over
Filtering by: Alternative title ssim Technical note no. 195 Remove constraint Alternative title ssim: Technical note no. 195 Academic Affiliation Electrical Engineering and Computer Science Remove constraint Academic Affiliation: Electrical Engineering and Computer Science Committee Member Tadepalli, Prasad Remove constraint Committee Member: Tadepalli, Prasad

Search Results

  • Visual object discovery and understanding

    Creator:
    Yuan, Jialin
    Abstract:
    Learning to recognize objects is a fundamental and essential step in human perception and understanding of the world. Accordingly, research of object discovery across diverse modalities plays a pivotal role in the context of computer vision. This field not only contributes significantly to enhancing our understanding of visual information but...
    Resource Type:
    Dissertation
    Full Text:
    almost as good as mask R-CNN without depending on a two-stage framework. Note that the training of the

  • 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:
    an unsupervised method, where no supervision about the data is available for learning

  • Using Change Representations to Analyze Properties of Variational Software

    Creator:
    Wang, Xiangyu
    Abstract:
    Appropriate representations of variational software simplify the analysis of their properties.This thesis proposes tailored representations of two kinds variational softwares: difference files of merge commits in Git and feature models. For the former, we use the Choice Edit Model, which is based on the choice calculus, to represent changes introduced...
    Resource Type:
    Masters Thesis
    Full Text:
    repositories shows that in some cases about 10% of merge conflicts having no semantical effects. For feature

  • Anomaly Detection: Theory, Explanation and User Feedback

    Creator:
    Siddiqui, Md Amran
    Abstract:
    Anomaly detection has been used in variety of applications in practice, including cyber-security, fraud detection and detecting faults in safety critical systems, etc. Anomaly detectors produce a ranked list of statistical anomalies, which are typically examined by human analysts in order to extract the actual anomalies of interest. Unfortunately, most...
    Resource Type:
    Dissertation
    Full Text:
    . Unfortunately, most anomaly detectors provide no explanations about why an instance was considered anomalous

  • Computing Resource Usage as a Factor of Student Success

    Creator:
    Moissinac, Béatrice
    Abstract:
    Learning Analytics and other branches of Educational Research such as Computing Education Research (CER) implicitly assume that students, especially college students, have no barriers to access learning platforms or software packages. This assumption may be attributed to such pervasive beliefs such as "everyone has a device", or "everyone can access...
    Resource Type:
    Dissertation
    Full Text:
    Research (CER) implicitly assume that students, especially college students, have no barriers to access

  • The density signature

    Creator:
    Migler-VonDollen, Theresa
    Abstract:
    In real networks, identifying dense regions is of great importance. For example, in a network that represents academic collaboration, authors within the densest component of the graph tend to be the most prolific. Dense subgraphs often identify communities in social networks. And dense subgraphs can be used to discover regulatory...
    Resource Type:
    Dissertation
    Full Text:
    the case in existing random graph models. No existing random graph model generates graphs that

  • Protein secondary structure prediction using conditional random fields and profiles

    Creator:
    Shen, Rongkun
    Abstract:
    Protein secondary structure prediction plays a pivotal role in predicting protein folding in three-dimensions. Its task is to assign each residue one of the three secondary structure classes helix, strand, or random coil. This is an instance of the problem of sequential supervised learning in machine learning. This thesis describes...
    Resource Type:
    Masters Thesis
    Full Text:
    , respectively. In addition, there was no apparent overfitting problem observed in our model. Besides

  • 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:
    have cannot-link constraints between one another. Note that if there exists no cannot-link constraints

  • 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:
    ) = w · φ(a), where w is the weight vector and φ(·) is a predefined feature function. Note that the

  • Improving automated email tagging with implicit feedback

    Creator:
    Sorower, Mohammad Shahed
    Abstract:
    Machine learning systems are generally trained offline using ground truth data that has been labeled by experts. However, these batch training methods are not a good fit for many applications, especially in the cases where complete ground truth data is not available for offline training. In addition, batch methods do...
    Resource Type:
    Dissertation
    Full Text:
    message, no corrections have been made, then perhaps it is safe for the learning system to treat the