The School of Informatics brings together research in Computer Science, Cognitive Science, Computational Linguistics and Artificial Intelligence. It provides a fertile environment for a wide range of interdisciplinary studies, leading to this new science of Informatics.

Recent Submissions

  • User experience driven CPU frequency scaling on mobile devices towards better energy efficiency 

    Seeker, Volker Günter (The University of Edinburgh, 2017-07-07)
    With the development of modern smartphones, mobile devices have become ubiquitous in our daily lives. With high processing capabilities and a vast number of applications, users now need them for both business and personal ...
  • Towards effective analysis of big graphs: from scalability to quality 

    Tian, Chao (The University of Edinburgh, 2017-11-30)
    This thesis investigates the central issues underlying graph analysis, namely, scalability and quality. We first study the incremental problems for graph queries, which aim to compute the changes to the old query answer, ...
  • Presentation of self on a decentralised web 

    Guy, Amy (The University of Edinburgh, 2017-11-30)
    Self presentation is evolving; with digital technologies, with the Web and personal publishing, and then with mainstream adoption of online social media. Where are we going next? One possibility is towards a world where ...
  • Syntax-mediated semantic parsing 

    Reddy Goli, Venkata Sivakumar (The University of Edinburgh, 2017-11-30)
    Querying a database to retrieve an answer, telling a robot to perform an action, or teaching a computer to play a game are tasks requiring communication with machines in a language interpretable by them. Semantic parsing ...
  • Syntactic complexity in the modal μ calculus 

    Lehtinen, Maria Karoliina (The University of Edinburgh, 2017-07-07)
    This thesis studies how to eliminate syntactic complexity in Lμ, the modal μ calculus. Lμ is a verification logic in which a least fixpoint operator μ, and its dual v, add recursion to a simple modal logic. The number ...
  • Specialised global methods for binocular and trinocular stereo matching 

    Horna Carranza, Luis Alberto (The University of Edinburgh, 2017-07-07)
    The problem of estimating depth from two or more images is a fundamental problem in computer vision, which is commonly referred as to stereo matching. The applications of stereo matching range from 3D reconstruction to ...
  • Statistical parametric speech synthesis using conversational data and phenomena 

    Dall, Rasmus (The University of Edinburgh, 2017-07-07)
    Statistical parametric text-to-speech synthesis currently relies on predefined and highly controlled prompts read in a “neutral” voice. This thesis presents work on utilising recordings of free conversation for the purpose ...
  • Scaling real-time event detection to massive streams 

    Wurzer, Dominik Stefan (The University of Edinburgh, 2017-11-30)
    In today’s world the internet and social media are omnipresent and information is accessible to everyone. This shifted the advantage from those who have access to information to those who do so first. Identifying new ...
  • Representation and execution of human know-how on the Web 

    Pareti, Paolo (The University of Edinburgh, 2018-07-02)
    Structured data has been a major component of web resources since the very beginning of the web. Metadata that was originally mostly meant for display purposes gradually expanded to incorporate the semantic content of a ...
  • Relationship descriptors for interactive motion adaptation 

    Al-Ashqar, Rami (The University of Edinburgh, 2017-07-07)
    In this thesis we present an interactive motion adaptation scheme for close interactions between skeletal characters and mesh structures, such as navigating restricted environments and manipulating tools. We propose a ...
  • Potential based prediction markets: a machine learning perspective 

    Hu, Jinli (The University of Edinburgh, 2017-11-30)
    A prediction market is a special type of market which offers trades for securities associated with future states that are observable at a certain time in the future. Recently, prediction markets have shown the promise ...
  • Reducing animator keyframes 

    Holden, Daniel (The University of Edinburgh, 2017-11-30)
    The aim of this doctoral thesis is to present a body of work aimed at reducing the time spent by animators manually constructing keyframed animation. To this end we present a number of state of the art machine learning ...
  • Programming language semantics as a foundation for Bayesian inference 

    Szymczak, Marcin (The University of Edinburgh, 2018-07-08)
    Bayesian modelling, in which our prior belief about the distribution on model parameters is updated by observed data, is a popular approach to statistical data analysis. However, writing specific inference algorithms for ...
  • Recurrent neural network language models for automatic speech recognition 

    Gangireddy, Siva Reddy (The University of Edinburgh, 2017-07-07)
    The goal of this thesis is to advance the use of recurrent neural network language models (RNNLMs) for large vocabulary continuous speech recognition (LVCSR). RNNLMs are currently state-of-the-art and shown to consistently ...
  • Localizing spatially and temporally objects and actions in videos 

    Kalogeiton, Vasiliki (The University of Edinburgh, 2018-07-02)
    The rise of deep learning has facilitated remarkable progress in video understanding. This thesis addresses three important tasks of video understanding: video object detection, joint object and action detection, and ...
  • Coding of multivariate stimuli and contextual interactions in the visual cortex 

    Keemink, Sander Wessel (The University of Edinburgh, 2018-07-02)
    The primary visual cortex (V1) has long been considered the main low level visual analysis area of the brain. The classical view is of a feedfoward system functioning as an edge detector, in which each cell has a receptive ...
  • Auxiliary variable Markov chain Monte Carlo methods 

    Graham, Matthew McKenzie (The University of Edinburgh, 2018-07-02)
    Markov chain Monte Carlo (MCMC) methods are a widely applicable class of algorithms for estimating integrals in statistical inference problems. A common approach in MCMC methods is to introduce additional auxiliary ...
  • Natural language generation as neural sequence learning and beyond 

    Zhang, Xingxing (The University of Edinburgh, 2017-11-30)
    Natural Language Generation (NLG) is the task of generating natural language (e.g., English sentences) from machine readable input. In the past few years, deep neural networks have received great attention from the natural ...
  • GRAPE: Parallel Graph Query Engine 

    Xu, Jingbo (The University of Edinburgh, 2017-11-30)
    The need for graph computations is evident in a multitude of use cases. To support computations on large-scale graphs, several parallel systems have been developed. However, existing graph systems require users to recast ...
  • Mechanisms of place recognition and path integration based on the insect visual system 

    Stone, Thomas Jonathan (The University of Edinburgh, 2017-11-30)
    Animals are often able to solve complex navigational tasks in very challenging terrain, despite using low resolution sensors and minimal computational power, providing inspiration for robots. In particular, many species ...

View more