Now showing items 21-40 of 1743

    • Great expectations: unsupervised inference of suspense, surprise and salience in storytelling 

      Wilmot, David (The University of Edinburgh, 2022-06-22)
      Stories interest us not because they are a sequence of mundane and predictable events but because they have drama and tension. Crucial to creating dramatic and exciting stories are surprise and suspense. Likewise, certain ...
    • Reclaiming scalability and privacy in the decentralized setting 

      Thyfronitis Litos, Orfeas Stefanos; Litos, Orfeas (The University of Edinburgh, 2022-07-11)
      The advent of blockchains has expanded the horizon of possibilities to novel decentralised applications and protocols that were not possible before. Designing and building such applications, be it for offering new ways for ...
    • Automated Testing for Solidity smart contracts 

      Akca, Sefa (The University of Edinburgh, 2022-06-21)
      Blockchains are the underlying technology for making secure online transactions using cryptocurrencies such as Bitcoins and Ethers. Executing, verifying, and enforcing credible transactions on permissionless blockchains ...
    • Tackling the veracity and variety of big data 

      Jin, Ruochun (The University of Edinburgh, 2022-06-21)
      This thesis tackles the veracity and variety challenges of big data, especially focusing on graphs and relational data. We start with proposing a class of graph association rules (GARs) to specify regularities between ...
    • Secure authentication and key agreement via abstract multi-agent interaction 

      Ahmed, Ibrahim Hassan (The University of Edinburgh, 2022-06-17)
      Authentication and key agreement are the foundation for secure communication over the Internet. Authenticated Key Exchange (AKE) protocols provide methods for communicating parties to authenticate each other, and establish ...
    • Hotscotch: exploiting workload characteristics to improve read-throughput 

      Pugh, Matthew (The University of Edinburgh, 2022-06-14)
      Key-value stores are ubiquitous at all layers of the computational stack; offering constant average lookup, insertion, and deletion time. This dissertation looks at how we can exploit skew in the workloads to improve the ...
    • Architectures for online simulation-based inference applied to robot motion planning 

      Asenov, Martin Andreev (The University of Edinburgh, 2022-06-13)
      Robotic systems have enjoyed significant adoption in industrial and field applications in structured environments, where clear specifications of the task and observations are available. Deploying robots in unstructured ...
    • Pronunciation modelling in end-to-end text-to-speech synthesis 

      Taylor, Jason (The University of Edinburgh, 2022-06-13)
      Sequence-to-sequence (S2S) models in text-to-speech synthesis (TTS) can achieve high-quality naturalness scores without extensive processing of text-input. Since S2S models have been proposed in multiple aspects of the ...
    • Practical synthesis from real-world oracles 

      Collie, Bruce (The University of Edinburgh, 2022-06-13)
      As software systems become increasingly heterogeneous, the ability of compilers to reason about an entire system has decreased. When components of a system are not implemented as traditional programs, but rather as specialised ...
    • Online dynamics model learning and control for robotics 

      Smith, Joshua (The University of Edinburgh, 2022-06-10)
      Robotic systems, of various sizes and types, are not only becoming more prominent in the research communities but have been further pushed into industrial and business uses. With the advent of more capable hardware able ...
    • Embodied agents in real-world robots: integrated control and machine learning for intelligent behaviours 

      Yuan, Kai (The University of Edinburgh, 2022-06-09)
      The central contribution of this thesis is providing a reliable framework and algorithms to make robots move as versatile and reliable as biological systems. To this end, this work proposes a hierarchical control framework ...
    • Robust and efficient inference and learning algorithms for generative models 

      Xu, Kai (The University of Edinburgh, 2022-06-09)
      Generative modelling is a popular paradigm in machine learning due to its natural ability to describe uncertainty in data and models and for its applications including data compression (Ho et al., 2020), missing data ...
    • Data-centric serverless cloud architecture 

      Ustiugov, Dmitrii (The University of Edinburgh, 2022-06-08)
      Serverless has become a new dominant cloud architecture thanks to its high scalability and flexible, pay-as-you-go billing model. In serverless, developers compose their cloud services as a set of functions while providers ...
    • Meta learning for few shot learning 

      Zhang, Xueting (The University of Edinburgh, 2022-06-08)
      Few-shot learning aims to scale visual recognition to open-ended growth of new classes with limited labelled examples, thus alleviating data and computation bottleneck of conventional deep learning. This thesis proposes a ...
    • Security and privacy of incentive-driven mechanisms 

      Lu, Yun (The University of Edinburgh, 2022-06-07)
      While cryptographic tools offer practical security and privacy supported by theory and formal proofs, there are often gaps between the theory and intricacies of the real world. This is especially apparent in the realm ...
    • Program analysis of probabilistic programs 

      Gorinova, Maria I. (The University of Edinburgh, 2022-05-25)
      Probabilistic programming is a growing area that strives to make statistical analysis more accessible, by separating probabilistic modelling from probabilistic inference. In practice this decoupling is difficult. The ...
    • Controlling and Learning Constrained Motions for Manipulation in Contact 

      Pousa de Moura, João Miguel (The University of Edinburgh, 2021-10-31)
      Many practical tasks in robotic systems involving contact interaction with the environment, such as cleaning windows, writing or grasping, are inherently constrained, in that both the task and the environment impose ...
    • A Model Comparison between Neural Architectures of Human Bilingual Sentence Processing 

      Roslund, Rasmus (The University of Edinburgh, 2021-11-30)
      This work investigates phenomena related to human bilingual sentence processing in neural language models. We ask ourselves the question if and how the emergence of these phenomena depends on the model architecture. For ...
    • Modelling and spatio-temporal analysis of spatial stochastic systems 

      Luisa Vissat, Ludovica (The University of Edinburgh, 2019-07-01)
      [No Deposit Agreement]
    • Data-to-text generation with neural planning 

      Puduppully, Ratish Surendran (The University of Edinburgh, 2022-04-11)
      In this thesis, we consider the task of data-to-text generation, which takes non-linguistic structures as input and produces textual output. The inputs can take the form of database tables, spreadsheets, charts, and so ...