Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 175 for “"structured data"”.

  1. Summarizing Semi-Structured Data

    Ph.D.

    buffalo Repository record for Summarizing Semi-Structured Data (opens in a new tab)

  2. Information overload in structured data

    … information overload problem in two separate structured domains, namely, graphs and text.</p> <p>Graph kernels have been proposed as an efficient and theoretically sound approach to compute graph similarity. They decompose graphs into certain sub-structures, such as subtrees, or subgraphs. …

    purdue-thes Repository record for Information overload in structured data (opens in a new tab)

  3. Deep learning and structured data

    In the recent years deep learning has witnessed successful applications in many different domains such as visual object recognition, detection and segmentation, automatic speech recognition, natural language processing, and reinforcement learning. In this thesis, we will investigate deep learning …

    mit Repository record for Deep learning and structured data (opens in a new tab)

  4. Techniques for structured data discovery

    The discovery of structured data, or data that is tagged by key-value pairs, is a problem that can be subdivided into two issues: how best to structure information architecture and user interaction for discovery; and how to intelligently display data in a way that that optimizes the discovery of …

    mit Repository record for Techniques for structured data discovery (opens in a new tab)

  5. Efficient Similarity Search in Structured Data

    Modern database applications are characterized by two major aspects: the use of complex data types with internal structure and the need for new data analysis methods. The focus of database users has shifted from simple queries to complex analyses of the data, known as knowledge discovery in …

    lmu-germany Repository record for Efficient Similarity Search in Structured Data (opens in a new tab)

  6. Kernel Methods for Tree Structured Data

    … information from large collections of noisy data. In many real world applications, data is naturally represented in structured form. Since traditional methods in machine learning deal with vectorial information, they require an a priori form of preprocessing. Among all the learning techniques …

    bologna Repository record for Kernel Methods for Tree Structured Data (opens in a new tab)

  7. Adapting Transformers for Structured Data Domains

    … and effectiveness of Transformers in structured data domains beyond their traditional use in natural language processing (NLP). We revisit key elements of the transformer framework - including input representations, attention formulations, auxiliary tasks, prediction layers and loss …

    vt Repository record for Adapting Transformers for Structured Data Domains (opens in a new tab)

  8. Scaling Multidimensional Inference for Big Structured Data

    <p>"In information technology, big data is a collection of data sets so large and complex that it becomes difficult to process using traditional data processing applications" [151]. In a</p><p>world of increasing sensor modalities, cheaper storage, and more data oriented questions, we are quickly …

    wustl Repository record for Scaling Multidimensional Inference for Big Structured Data (opens in a new tab)

  9. Focus-based Interactive Visualization for Structured Data

    … that studies visual representations of abstract data where no spatial representation is available, has been playing an essential role in assisting people to understand the vast amount of information created by modern technology. Visualizing large complex structured data is an important area as …

    ohiolink Repository record for Focus-based Interactive Visualization for Structured Data (opens in a new tab)

  10. Learning from Structured Data with Weak Supervision

    … to test them, and collect and interpret data. Fundamental advances over the past decade include self-supervised learning methods that train models on broad data at scale without pre-defined labels, geometric deep learning that leverages structure and geometry informed by scientific …

    cambridge Repository record for Learning from Structured Data with Weak Supervision (opens in a new tab)

  11. Towards Scalable Structured Data from Clinical Text

    … many pertinent variables are trapped in unstructured clinical note text. Automated extraction is difficult since clinical notes are written in their own jargon-heavy dialect, patient histories can contain hundreds of notes, and there is often minimal labeled data. In this thesis, I tackle …

    mit Repository record for Towards Scalable Structured Data from Clinical Text (opens in a new tab)

  12. Modeling Structured Data with Invertible Generative Models

    Data is complex and has a variety of structures and formats. Modeling datasets is a core problem in modern artificial intelligence. Generative models are machine learning models, which model datasets with probability distributions. Deep generative models combine deep learning with probability …

    vt Repository record for Modeling Structured Data with Invertible Generative Models (opens in a new tab)

  13. Algorithms on graph-structured data with imperfect information

    Graph-structured data is able to characterize pairwise or even higher-order relations among different data points, and has been demonstrated to be highly advantageous in various data mining and machine learning applications. Such graph-structured data may either come from real life networks, or …

    uiuc Repository record for Algorithms on graph-structured data with imperfect information (opens in a new tab)

  14. Semi-automatic matching of semi-structured data updates

    Data matching, also referred to as data linkage or field matching, is a technique used to combine multiple data sources into one data set. Data matching is used for data integration in a number of sectors and industries; from politics and health care to scientific applications. The motivation for …

    cape-town Repository record for Semi-automatic matching of semi-structured data updates (opens in a new tab)

  15. Automated extraction of structured data from HTML documents

    Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1998.

    mit Repository record for Automated extraction of structured data from HTML documents (opens in a new tab)

  16. Fusion Tables : new ways to collaborate on structured data

    Fusion Tables allows data collaborators to create, merge, navigate and set access control permissions on structured data. This thesis focuses on the collaboration tools that were added to Googles Fusion Tables. The collaboration tools provided additional functionality: first, the ability to view, …

    mit Repository record for Fusion Tables : new ways to collaborate on structured data (opens in a new tab)

  17. Modeling tools for the integration of structured data sources

    Disparity in representations within structured documents such as XML or SQL makes interoperability challenging, error-prone and expensive. A model is developed to process disparate representations to an encompassing generic knowledge representation. Data sources were characterized according to a …

    mit Repository record for Modeling tools for the integration of structured data sources (opens in a new tab)

  18. Towards Efficient and Scalable Deep Learning on Graph-Structured Data

    … Effective and Scalable Deep Learning on Graph-Structured Data," proposes novel methodologies to address these limitations across four main research thrusts. To address scalability in learning node embeddings, one paper introduces CCA-SSG, a self-supervised framework that learns robust node …

    uic

  19. A generalization based hybrid algorithm for clustering semi-structured data

    … construction, object generalization and data clustering is presented. The algorithm works well on semi-structured data and requires only a minimum of domain knowledge. Since the algorithm reduces the dimensionality of the semi-structured data, clustering of the resulting generalized data

    must-thes Repository record for A generalization based hybrid algorithm for clustering semi-structured data (opens in a new tab)

Page 1 of 9