Search for dissertations about: "data-driven methods"

Showing result 1 - 5 of 85 swedish dissertations containing the words data-driven methods.

  1. 1. Data Driven Visual Recognition

    University dissertation from KTH Royal Institute of Technology

    Author : Omid Aghazadeh; KTH.; [2014]
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Visual Recognition; Data Driven; Supervised Learning; Mixture Models; Non-Parametric Models; Category Recognition; Novelty Detection;

    Abstract : This thesis is mostly about supervised visual recognition problems. Based on a general definition of categories, the contents are divided into two parts: one which models categories and one which is not category based. We are interested in data driven solutions for both kinds of problems. READ MORE

  2. 2. Data-driven syntactic analysis

    University dissertation from Institutionen för talöverföring och musikakustik

    Author : Beata Megyesi; KTH.; [2002]
    Keywords : natural language processing; machine learning; data-driven methods; part-of-speech tagging; chunking; shallow parsing; evaluation; hidden Markov modeling; maximum entropy learning; memory-based learning; transformation-based learning; morphology; syn;

    Abstract : .... READ MORE

  3. 3. Data-driven Methods in Inverse Problems

    University dissertation from Stockholm : KTH Royal Institute of Technology

    Author : Jonas Adler; KTH.; [2019]
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Inverse Problems; Machine Learning; Tomography;

    Abstract : In this thesis on data-driven methods in inverse problems we introduce several new methods to solve inverse problems using recent advancements in machine learning and specifically deep learning. The main goal has been to develop practically applicable methods, scalable to medical applications and with the ability to handle all the complexities associated with them. READ MORE

  4. 4. Argument Differentiation. Soft constraints and data-driven models

    University dissertation from Göteborg : University of Gothenburg

    Author : Lilja Øvrelid; Göteborgs universitet.; Gothenburg University.; [2008]
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; syntactic arguments; parsing; lexical acquisition; animacy; Scandinavian syntax; soft constraints; data-driven models; machine learning;

    Abstract : The ability to distinguish between different types of arguments is central to syntactic analysis, whether studied from a theoretical or computational point of view. This thesis investigates the influence and interaction of linguistic properties of syntactic arguments in argument differentiation. READ MORE

  5. 5. Data-driven Methods for Spoken Dialogue Systems Applications in Language Understanding, Turn-taking, Error Detection, and Knowledge Acquisition

    University dissertation from Stockholm : KTH Royal Institute of Technology

    Author : Raveesh Meena; KTH.; [2016]
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Language Understanding; Turn-taking; Error Detection; Knowledge Acquisition; Crowdsourcing; semantisk tolkning talspråk; turtagning i dialogsystem; fel och missförstånd; crowdsourcing; dialogsystem; Tal- och musikkommunikation; Speech and Music Communication;

    Abstract : Spoken dialogue systems are application interfaces that enable humans to interact with computers using spoken natural language. A major challenge for these systems is dealing with the ubiquity of variability—in user behavior, in the performance of the various speech and language processing sub-components, and in the dynamics of the task domain. READ MORE