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.

Collections in this Community

Recent Submissions

  • Co-designing reliability and performance for datacenter memory 

    Patil, Adarsh (The University of Edinburgh, 2023-09-25)
    Memory is one of the key components that affects reliability and performance of datacenter servers. Memory in today’s servers is organized and shared in several ways to provide the most performant and efficient access to ...
  • Learning robotic motor skills for dynamic grasping, catching, and dexterous in-hand manipulation 

    Hu, Wenbin (The University of Edinburgh, 2023-09-19)
    Endowing robots with human-level grasping and manipulation skills is an appealing yet challenging research topic over decades. Towards more extensive functionalities, the robots should interact with the objects and environment ...
  • Arabic sarcasm detection 

    Abu Farha, Ibrahim (The University of Edinburgh, 2023-09-19)
    Sarcasm is a form of verbal irony that is often used to express ridicule or contempt. When using sarcasm, a speaker expresses their opinion in an indirect way, where the literal meaning is different from the intended one. ...
  • Optimization strategies for large scale distributed systems 

    Verbowski, Chad (The University of Edinburgh, 2023-09-14)
    Every day we rely on large distributed software services for communication, information, commerce, entertainment, and many other personal and business use cases. These services are globally available, sometimes with billions ...
  • Strategy complexity of lim sup and lim inf payoff objectives in countable MDPs 

    Munday, Eric (The University of Edinburgh, 2023-08-30)
    We study countably infinite Markov decision processes (MDPs) with real-valued tran- sition rewards. A strategy is a function which decides how plays proceed within the MDP. Every strategy induces a set of infinite runs ...
  • Robust SLAM and motion segmentation under long-term dynamic large occlusions 

    Long, Ran (The University of Edinburgh, 2023-08-29)
    Visual sensors are key to robot perception, which can not only help robot localisation but also enable robots to interact with the environment. However, in new environments, robots can fail to distinguish the static and ...
  • Nesting optimization with adversarial games, meta-learning, and deep equilibrium models 

    Micaelli, Paul (The University of Edinburgh, 2023-08-29)
    Nested optimization, whereby an optimization problem is constrained by the solutions of other optimization problems, has recently seen a surge in its application to Deep Learning. While the study of such problems started ...
  • Data-driven modelling and control of concentric tube robots with application in distal lung sampling 

    Thamo, Balint (The University of Edinburgh, 2023-08-14)
    This research aims to explore the use of Concentric Tube Robots (CTRs) as a novel alternative to needle-based interventions in order to make these procedures more accurate and repeatable. CTRs due to their small footprint, ...
  • Rigorous treatment of Meek's method for single transferable vote with formal proofs of key properties 

    Palmer, Jake Evan (The University of Edinburgh, 2023-08-14)
    This thesis presents a mechanised formalisation of key concepts and properties of Meek's method of Single Transferable Vote (STV). This method is currently in use in a number of local elections in New Zealand, the Royal ...
  • Automated identification and behaviour classification for modelling social dynamics in group-housed mice 

    Camilleri, Michael (The University of Edinburgh, 2023-08-08)
    Mice are often used in biology as exploratory models of human conditions, due to their similar genetics and physiology. Unfortunately, research on behaviour has traditionally been limited to studying individuals in isolated ...
  • Online receding horizon planning of multi-contact locomotion 

    Wang, Jiayi (The University of Edinburgh, 2023-08-07)
    Legged robots can traverse uneven terrain by using multiple contacts between their limbs and the environment. Nevertheless, to enable reliable operation in the real world, legged robots necessarily require the capability ...
  • Guided rewriting and constraint satisfaction for parallel GPU code generation 

    Mogers, Naums (The University of Edinburgh, 2023-07-28)
    Graphics Processing Units (GPUs) are notoriously hard to optimise for manually due to their scheduling and memory hierarchies. What is needed are good automatic code generators and optimisers for such parallel hardware. ...
  • Computation and data efficient techniques for training computer vision methods 

    Kocyigit, Mustafa Taha (The University of Edinburgh, 2023-07-11)
    Increased use of data and computation have been the main drivers in Deep Learning for improving performance, solving previously unsolvable problems and unlocking new capabilities. At the same time cost of training and ...
  • Probabilistic modelling of single cell multi-omics data 

    Maniatis, Christos (The University of Edinburgh, 2023-07-11)
    Multicellular organisms possess a diverse set of cells exhibiting unique properties and function. Despite their physiology and role each cell owns the same copy of genetic in- structions encoded in its DNA. The ability ...
  • Advances in scalable learning and sampling of unnormalised models 

    Rhodes, Benjamin (The University of Edinburgh, 2023-07-10)
    We study probabilistic models that are known incompletely, up to an intractable normalising constant. To reap the full benefit of such models, two tasks must be solved: learning and sampling. These two tasks have been subject ...
  • Neuromorphic mushroom body model learning spatio-temporal memory 

    Zhu, Le (The University of Edinburgh, 2023-06-30)
    The utilisation of bio-robots is well-suited for linking the evaluation of biological findings with the advance of engineering solutions. Designing a mobile navigation robot that can adapt to the real-world natural environment ...
  • Secure storage systems for untrusted cloud environments 

    Bailleu, Maurice (The University of Edinburgh, 2023-06-30)
    The cloud has become established for applications that need to be scalable and highly available. However, moving data to data centers owned and operated by a third party, i.e., the cloud provider, raises security concerns ...
  • Theory of localisable monads 

    Dicaire, Nuiok (The University of Edinburgh, 2023-06-30)
    Monads are used in programming semantics to govern computational side-effects such as reading and writing to a memory store, non-determinism, exceptions, and interactive inputs and outputs among others. Monads are also ...
  • Modular lifelong machine learning 

    Valkov, Lazar Ignatov (The University of Edinburgh, 2023-06-22)
    Deep learning has drastically improved the state-of-the-art in many important fields, including computer vision and natural language processing (LeCun et al., 2015). However, it is expensive to train a deep neural network ...
  • Interpretable and verifiable planning and prediction for autonomous vehicles 

    Brewitt, Cillian (The University of Edinburgh, 2023-06-16)
    Autonomous driving (AD) has gained much attention in recent years due to its many potential benefits such as improving safety and increasing efficiency. However, AD is a difficult problem with challenges such as handling ...

View more