Advanced search

Showing result 1 - 5 of 243 swedish dissertations matching the above criteria.

  2. 1. Mapping incomplete relational data : networks in ecology & evolution

    Author : Daniel Edler; Martin Rosvall; Alexandre Antonelli; Renaud Lambiotte; Umeå universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; network science; information theory; map equation; community detection; biogeography; evolution;

    Abstract : We live in an interconnected world full of complex systems that cannot be understood simply by analyzing their components. From how genes regulate biological functions to the distribution of life on Earth, we need methods that can analyze systems as a whole. READ MORE

  4. 2. Anomaly detection in trajectory data for surveillance applications

    Author : Rikard Laxhammar; Örebro universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Anomaly detection; trajectory analysis; statistical methods; conformal prediction; automated surveillance; Computer science; Datavetenskap; Datalogi; Computer and Systems Science; Teknik;

    Abstract : Abnormal behaviour may indicate important objects and events in a wide variety of domains. One such domain is intelligence and surveillance, where there is a clear trend towards more and more advanced sensor systems producing huge amounts of trajectory data from moving objects, such as people, vehicles, vessels and aircraft. READ MORE

  5. 3. Predicting Linguistic Structure with Incomplete and Cross-Lingual Supervision

    Author : Oscar Täckström; Joakim Nivre; Jussi Karlgren; Ryan McDonald; Hal Daumé III; Uppsala universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; linguistic structure prediction; structured prediction; latent-variable model; semi-supervised learning; multilingual learning; cross-lingual learning; indirect supervision; partial supervision; ambiguous supervision; part-of-speech tagging; dependency parsing; named-entity recognition; sentiment analysis; Computational Linguistics; Datorlingvistik;

    Abstract : Contemporary approaches to natural language processing are predominantly based on statistical machine learning from large amounts of text, which has been manually annotated with the linguistic structure of interest. However, such complete supervision is currently only available for the world's major languages, in a limited number of domains and for a limited range of tasks. READ MORE

  6. 4. A Picture is Worth a Thousand Words: Natural Language Processing in Context

    Author : Lovisa Hagström; Chalmers tekniska högskola; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NLP; Knowledge representation; Neural network; Vision-and-language models; Grounding; BERT;

    Abstract : Modern NLP models learn language from lexical co-occurrences. While this method has allowed for significant breakthroughs, it has also exposed potential limitations of modern NLP methods. For example, NLP models are prone to hallucinate, represent a biased world view and may learn spurious correlations to solve the data instead of the task at hand. READ MORE

  7. 5. A Prescriptive Approach to Eliciting Decision Information

    Author : Mona Riabacke; Mats Danielson; Alec Morton; Stockholms universitet; []
    Keywords : NATURVETENSKAP; NATURAL SCIENCES; Decision Analysis; prescriptive; elicitation methods; multi-criteria; Computer and Systems Sciences; data- och systemvetenskap;

    Abstract : The amount of information involved in many decision making situations has increased dramatically in recent years and support of some kind is often needed. Consequently, fields like Business Intelligence (BI) and Decision Support Systems (DSS) have advanced. READ MORE