Informatics thesis and dissertation collection
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.
This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
Recent Submissions
-
Flexible neural architectures for sequence modeling
(The University of Edinburgh, 2020-06-25)Auto-regressive sequence models can estimate the distribution of any type of sequential data. To study sequence models, we consider the problem of language modeling, which entails predicting probability distributions over ... -
Accelerating and simulating detected physical interations
(The University of Edinburgh, 2020-06-25)The aim of this doctoral thesis is to present a body of work aimed at improving performance and developing new methods for animating physical interactions using simulation in virtual environments. To this end we develop a ... -
Modelling the neuromechanics of exploration and taxis in larval Drosophiila
(The University of Edinburgh, 2020-06-25)The Drosophila larva is emerging as a useful tool in the study of complex behaviours, due to its relatively small size, its genetic tractability, and its varied behavioural repertoire. The larva executes a stereotypical ... -
Experience-driven optimal motion synthesis in complex and shared environments
(The University of Edinburgh, 2020-06-25)Optimal loco-manipulation planning and control for high-dimensional systems based on general, non-linear optimisation allows for the specification of versatile motion subject to complex constraints. However, complex, ... -
Deep neural mobile networking
(The University of Edinburgh, 2020-06-25)The next generation of mobile networks is set to become increasingly complex, as these struggle to accommodate tremendous data traffic demands generated by ever-more connected devices that have diverse performance requirements ... -
Neural document modeling and summarization
(The University of Edinburgh, 2020-06-25)Document summarization is the task of automatically generating a shorter version of a document or multiple documents while retaining the most important information. The task has received much attention in the natural ... -
Perceptual Bayesian inference in autism and schizophrenia
(The University of Edinburgh, 2020-06-25)Recent theories in the field of computational psychiatry regard schizophrenia (SCZ) and autistic spectrum disorders (ASD) as impairments in Bayesian inference performed by the brain. In Bayesian terms, perception is a ... -
Modelling speaker adaptation in second language learner dialogue
(The University of Edinburgh, 2020-06-25)Understanding how tutors and students adapt to one another within Second Language (L2) learning is an important step in the development of better automated tutoring tools for L2 conversational practice. Such an understanding ... -
From constraint programming to heterogeneous parallelism
(The University of Edinburgh, 2020-06-25)The scaling limitations of multi-core processor development have led to a diversification of the processor cores used within individual computers. Heterogeneous computing has become widespread, involving the cooperation ... -
3D scene graph inference and refinement for vision-as-inverse-graphics
(The University of Edinburgh, 2020-06-25)The goal of scene understanding is to interpret images, so as to infer the objects present in a scene, their poses and fine-grained details. This thesis focuses on methods that can provide a much more detailed ... -
Multi-view representation learning for natural language processing applications
(The University of Edinburgh, 2020-06-25)The pervasion of machine learning in a vast number of applications has given rise to an increasing demand for the effective processing of complex, diverse and variable datasets. One representative case of data diversity ... -
Analytics of student interactions: towards theory-driven, actionable insights
(The University of Edinburgh, 2020-06-25)The field of learning analytics arose as a response to the vast quantities of data that are increasingly generated about students, their engagement with learning resources, and their learning and future career outcomes. ... -
Development of machine learning schemes for segmentation, characterisation, and evolution prediciton of white matter hyperintensities in structural brain MRI
(The University of Edinburgh, 2020-06-25)White matter hyperintensities (WMH) are neuroradiological features seen in T2 Fluid-Attenuated Inversion Recovery (T2-FLAIR) brain magnetic resonance imaging (MRI) and have been commonly associated with stroke, ageing, ... -
On three use cases of multi-connectivity paradigm in emerging wireless networks
(The University of Edinburgh, 2020-06-25)As envisioned by global network operators, the increasing trend of data traffic demand is expected to continue with exponential growth in the coming years. To cope with this rapid increase, significant efforts from the ... -
Modular robots for sorting
(The University of Edinburgh, 2020-06-25)Current industrial sorting systems allow for low error, high throughput sorts with tightly constrained properties. These sorters, however, are often hardware limited to certain items and criteria. There is a need for ... -
Deep learning for compilers
(The University of Edinburgh, 2020-06-25)Constructing compilers is hard. Optimising compilers are multi-million dollar projects spanning years of development, yet remain unable to fully exploit the available performance, and are prone to bugs. The rapid transition ... -
Modelling and measurement in synthetic biology
(The University of Edinburgh, 2020-02-10)Synthetic biology applies engineering principles to make progress in the study of complex biological phenomena. The aim is to develop understanding through the praxis of construction and design. The computational branch ... -
Low-resource speech translation
(The University of Edinburgh, 2019-12-17)We explore the task of speech-to-text translation (ST), where speech in one language (source) is converted to text in a different one (target). Traditional ST systems go through an intermediate step where the source ... -
On understanding character-level models for representing morphology
(The University of Edinburgh, 2020-01-20)Morphology is the study of how words are composed of smaller units of meaning (morphemes). It allows humans to create, memorize, and understand words in their language. To process and understand human languages, we expect ... -
Understanding and generating language with abstract meaning representation
(The University of Edinburgh, 2020-01-08)Abstract Meaning Representation (AMR) is a semantic representation for natural language that encompasses annotations related to traditional tasks such as Named Entity Recognition (NER), Semantic Role Labeling (SRL), word ...
