Now showing items 1-20 of 1528

  • Exploring the optimization space of multi-core architectures with OpenCL benchmarks 

    Panickal, Deepak (The University of Edinburgh, 2011)
    Open Computing Language (OpenCL) is an open standard for writing portable software for heterogeneous architectures such as Central Processing Units (CPUs) and Graphic Processing Units (GPUs). Programs written in OpenCL ...
  • Learning about the learning process: from active querying to fine-tuning 

    Pang, Kunkun (The University of Edinburgh, 2019-07-01)
    The majority of research on academic machine learning addresses the core model fitting part of the machine learning workflow. However, prior to model fitting, data collection and annotation is an important step; and ...
  • Weakly supervised sentiment analysis and opinion extraction 

    Angelidis, Stefanos (The University of Edinburgh, 2019-07-01)
    In recent years, online reviews have become the foremost medium for users to express their satisfaction, or lack thereof, about products and services. The proliferation of user-generated reviews, combined with the rapid ...
  • In search of the optimal acoustic features for statistical parametric speech synthesis 

    Espic Calderón, Felipe Sebastián (The University of Edinburgh, 2019-07-01)
    In the Statistical Parametric Speech Synthesis (SPSS) paradigm, speech is generally represented as acoustic features and the waveform is generated by a vocoder. A comprehensive summary of state-of-the-art vocoding ...
  • Contextual citation recommendation using scientific discourse annotation schemes 

    Duma, Daniel Cristian (The University of Edinburgh, 2019-07-01)
    All researchers have experienced the problem of fishing out the most relevant scientific papers from an ocean of publications, and some may have wished that their text editor suggested these papers automatically. This ...
  • Language-integrated provenance 

    Fehrenbach, Stefan (The University of Edinburgh, 2019-07-01)
    Provenance is metadata about the where, the why, and the how of data. It is evidence which can answer questions such as: Where exactly did this piece of data come from? Why is this row in my result? How was it produced? ...
  • Statistical modelling of neuronal population activity: from data analysis to network function 

    Sorbaro Sindaci, Martino (The University of Edinburgh, 2019-07-01)
    The term statistical modelling refers to a number of abstract models designed to reproduce and understand the statistical properties of the activity of neuronal networks at the population level. Large-scale recordings ...
  • Stochastic modelling of spatial collective adaptive systems 

    Zoń, Natalia (The University of Edinburgh, 2019-07-01)
    Collective Adaptive Systems (CAS) are composed of individual agents with internal knowledge and rules which organize themselves into ensembles. These ensembles can often be observed to exhibit behaviour resembling that ...
  • Resource management in future mobile networks: from millimetre-wave backhauls to airborne access networks 

    Li, Rui (The University of Edinburgh, 2019-07-01)
    The next generation of mobile networks will connect vast numbers of devices and support services with diverse requirements. Enabling technologies such as millimetre-wave (mm-wave) backhauling and network slicing allow ...
  • Models for reinforcement learning and design of a soft robot inspired by Drosophila larvae 

    Wei, Tianqi (The University of Edinburgh, 2019-07-01)
    Designs for robots are often inspired by animals, as they are designed mimicking animals’ mechanics, motions, behaviours and learning. The Drosophila, known as the fruit fly, is a well-studied model animal. In this thesis, ...
  • Data driven mapping of the drosophila larval central nervous system 

    Wood, David George (The University of Edinburgh, 2019-07-01)
    The Central Nervous System (CNS) of the larval Drosophila model organism is extensively studied partly due to its small size and short generation times but also due to its ability to learn and the availability of genetic ...
  • Fast machine translation on parallel and massively parallel hardware 

    Bogoychev, Nikolay Veselinov (The University of Edinburgh, 2019-07-01)
    Parallel systems have been widely adopted in the field of machine translation, because the raw computational power they offer is well suited to this computationally intensive task. However programming for parallel hardware ...
  • Verification problems for timed and probabilistic extensions of Petri Nets 

    Ciobanu, Radu (The University of Edinburgh, 2019-07-01)
    In the first part of the thesis, we prove the decidability (and PSPACE-completeness) of the universal safety property on a timed extension of Petri Nets, called Timed Petri Nets. Every token has a real-valued clock (a.k.a. ...
  • Learning structured task related abstractions 

    Penkov, Svetlin Valentinov (The University of Edinburgh, 2019-07-01)
    As robots and autonomous agents are to assist people with more tasks in various domains they need the ability to quickly gain contextual awareness in unseen environments and learn new tasks. Current state of the art ...
  • Typed concurrent functional programming with channels, actors and sessions 

    Fowler, Simon John (The University of Edinburgh, 2019-07-01)
    The age of writing single-threaded applications is over. To develop scalable applications, developers must make use of concurrency and parallelism. Nonetheless, introducing concurrency and parallelism is difficult: naïvely ...
  • Way of the dagger 

    Karvonen, Martti Johannes (The University of Edinburgh, 2019-07-01)
    A dagger category is a category equipped with a functorial way of reversing morphisms, i.e. a contravariant involutive identity-on-objects endofunctor. Dagger categories with additional structure have been studied under ...
  • On accuracy, robustness and reliability of laser-based localization 

    Nobili, Simona (The University of Edinburgh, 2019-07-01)
    Legged robots are expected to demonstrate autonomous skills in situations which are not suitable for wheeled platforms, such as cluttered disaster areas and outdoor trails. State estimation strategies for legged robots ...
  • Visual context for verb sense disambiguation and multilingual representation learning 

    Gella, Spandana (The University of Edinburgh, 2019-07-01)
    Every day billions of images are uploaded to the web. To process images at such a large scale it is important to build automatic image understanding systems. An important step towards understanding the content of the ...
  • Spatial statistical modelling of epigenomic variability 

    Kapourani, Chantriolnt Andreas (The University of Edinburgh, 2019-07-01)
    Each cell in our body carries the same genetic information encoded in the DNA, yet the human organism contains hundreds of cell types which differ substantially in physiology and functionality. This variability stems ...
  • Developing a framework for semi-automated rule-based modelling for neuroscience research 

    Wysocka, Emilia Malgorzata (The University of Edinburgh, 2019-07-01)
    Dynamic modelling has significantly improved our understanding of the complex molecular mechanisms underpinning neurobiological processes. The detailed mechanistic insights these models offer depend on the availability ...