Now showing items 1-20 of 1644

    • Training dynamics of neural language models 

      Saphra, Naomi (The University of Edinburgh, 2021-07-31)
      Why do artificial neural networks model language so well? We claim that in order to answer this question and understand the biases that lead to such high performing language models---and all models that handle language---we ...
    • Graph-based broad-coverage semantic parsing 

      Lyu, Chunchuan (The University of Edinburgh, 2021-07-31)
      Many broad-coverage meaning representations can be characterized as directed graphs, where nodes represent semantic concepts and directed edges represent semantic relations among the concepts. The task of semantic parsing ...
    • Using a quadcopter to model the visual navigation behaviours of flying insects 

      Stankiewicz, Jan (The University of Edinburgh, 2021-07-31)
      Micro aerial vehicles (MAVs) have become increasingly prominent in the last decade, with several sectors now routinely using this technology for applications such as filming, surveying and maintenance. A significant barrier ...
    • Algorithms for learning from spatial and mobility data 

      Astefanoaei, Maria (The University of Edinburgh, 2020-11-30)
      Data from the numerous mobile devices, location-based applications, and collection sensors used currently can provide important insights about human and natural processes. These insights can inform decision making in ...
    • Representational principles of function generalization 

      León-Villagrá, Pablo (The University of Edinburgh, 2020-11-30)
      Generalization is at the core of human intelligence. When the relationship between continuous-valued data is generalized, generalization amounts to function learning. Function learning is important for understanding human ...
    • Learning to adapt: meta-learning approaches for speaker adaptation 

      Klejch, Ondrej (The University of Edinburgh, 2020-11-30)
      The performance of automatic speech recognition systems degrades rapidly when there is a mismatch between training and testing conditions. One way to compensate for this mismatch is to adapt an acoustic model to test ...
    • Learning dynamic motor skills for terrestrial locomotion 

      Yang, Chuanyu (The University of Edinburgh, 2020-11-30)
      The use of Deep Reinforcement Learning (DRL) has received significantly increased attention from researchers within the robotics field following the success of AlphaGo, which demonstrated the superhuman capabilities of ...
    • Space and time in monoidal categories 

      Enrique Moliner, Pau (The University of Edinburgh, 2021-07-31)
      The use of categorical methods is becoming more prominent and successful in both physics and computer science. The basic idea is that objects of a category can represent systems, and morphisms can model the processes that ...
    • Querying graphs on large-scale data 

      Li, Yuanhao (The University of Edinburgh, 2021-07-31)
      This doctoral thesis will present the results of my work into querying graphs on large-scale data, from both the data perspective and query perspective. We first propose a scheme to reduce large graphs into small ones. ...
    • Automating the repair of faulty logical theories 

      Li, Xue (The University of Edinburgh, 2021-07-31)
      This thesis aims to develop a domain-independent system for repairing faulty Datalog-like theories by combining three existing techniques: abduction, belief revision and conceptual change. Accordingly, the proposed system ...
    • Generative neural data synthesis for autonomous systems 

      Jegorova, Marija (The University of Edinburgh, 2020-11-30)
      A significant number of Machine Learning methods for automation currently rely on data-hungry training techniques. The lack of accessible training data often represents an insurmountable obstacle, especially in the fields ...
    • Interactive robot learning with human alignment 

      Hristov, Yordan (The University of Edinburgh, 2021-07-31)
      [No Deposit Agreement]
    • Understanding and generating language with Discourse Representation Structures 

      Liu, Jiangming (The University of Edinburgh, 2021-07-31)
      [No Deposit Agreement]
    • Dyadic collaborative manipulation formalism for optimizing human-robot teaming 

      Stouraitis, Theodoros (The University of Edinburgh, 2021-07-31)
      Dyadic collaborative Manipulation (DcM) is a term we use to refer to a team of two individuals, the agent and the partner, jointly manipulating an object. The two individuals partner together to form a distributed system, ...
    • Deep representation learning for speech recognition 

      Równicka, Joanna Małgorzata (The University of Edinburgh, 2021-07-31)
      Representation learning is a fundamental ingredient of deep learning. However, learning a good representation is a challenging task. For speech recognition, such a representation should contain the information needed to ...
    • Towards larger scale collective operations in the Message Passing Interface 

      Rüfenacht, Martin Peter Albert (The University of Edinburgh, 2021-07-31)
      Supercomputers continue to expand both in size and complexity as we reach the beginning of the exascale era. Networks have evolved, from simple mechanisms which transport data to subsystems of computers which fulfil a ...
    • Knowledge-enhanced neural grammar Induction 

      Li, Bowen (The University of Edinburgh, 2021-07-31)
      Natural language is usually presented as a word sequence, but the inherent structure of language is not necessarily sequential. Automatic grammar induction for natural language is a long-standing research topic in the ...
    • Reachability analysis of branching probabilistic processes 

      Martinov, Emanuel Ognyanov (The University of Edinburgh, 2021-07-31)
      We study a fundamental class of infinite-state stochastic processes and stochastic games, namely Branching Processes, under the properties of (single-target) reachability and multi-objective reachability. In particular, ...
    • Domain-aware ontology matching 

      Quesada Real, Francisco José (The University of Edinburgh, 2021-07-31)
      During the last years, technological advances have created new ways of communication, which have motivated governments, companies and institutions to digitalise the data they have in order to make it accessible and ...
    • Monitoring depressive symptoms using social media data 

      Chen, Lushi (The University of Edinburgh, 2021-07-31)
      Social media data contains rich information about one's emotions and daily life experiences. In the recent decade, researchers have found links between people's behavior on social media platforms and their mental health ...