Informatics, School of: Recent submissions
Now showing items 1-20 of 1794
-
Toward relevant answers to queries on incomplete databases
(The University of Edinburgh, 2023-05-24)Incomplete and uncertain information is ubiquitous in database management applications. However, the techniques specifically developed to handle incomplete data are not sufficient. Even the evaluation of SQL queries on ... -
Automatic generation of highly concurrent, hierarchical and heterogeneous cache coherence protocols from atomic specifications
(The University of Edinburgh, 2023-05-24)Cache coherence protocols are often specified using only stable states and atomic transactions for a single cache hierarchy level. Designing highly-concurrent, hierarchical and heterogeneous directory cache coherence ... -
Bayesian density regression with functional covariates - modelling and visualisation
(The University of Edinburgh, 2023-05-24)This thesis develops models, techniques, and visualization tools for nonparametric Bayesian regression with a scalar response and a functional covariate (possibly subject to measurement error). In particular, one of the ... -
Advances in open ad hoc teamwork and teammate generation
(The University of Edinburgh, 2023-05-15)Many real-world problems require an agent that can adapt its policy to efficiently collaborate with different groups of teammates whose composition may change over time. Previous work to design agents with such adaptive ... -
Data cleaning with variational autoencoders
(The University of Edinburgh, 2023-04-25)A typical data science or machine learning pipeline starts with data exploration; then data engineering (wrangling, cleaning); then moves towards modelling (model selection, learning, validation); and finally model ... -
Towards trustworthy computing on untrustworthy hardware
(The University of Edinburgh, 2023-04-25)Historically, hardware was thought to be inherently secure and trusted due to its obscurity and the isolated nature of its design and manufacturing. In the last two decades, however, hardware trust and security have ... -
Computational sarcasm detection and understanding in online communication
(The University of Edinburgh, 2023-04-25)The presence of sarcasm in online communication has motivated an increasing number of computational investigations of sarcasm across the scientific community. In this thesis, we build upon these investigations. Pointing ... -
Understanding the fundamentals of bipedal locomotion in humans and robots
(The University of Edinburgh, 2023-04-25)Walking is a robust and efficient method of moving around the world, which would greatly enhance the capabilities of humanoid robots, although they cannot match the performance of their biological counterparts. The highly ... -
Unsupervised category-level viewpoint estimation
(The University of Edinburgh, 2023-04-25)The recent progress in deep learning techniques transformed the field of computer vision, with tasks like object classification or segmentation being almost considered solved. This however requires sufficiently many ... -
Technosocial development in an open society: augmenting our practice with tools to acknowledge the technosocial nature of development. Demonstrated by studies of the values of scholarly practice, and how they are reconstructed by attempts to open scholarly society
(The University of Edinburgh, 2016-06-27)Social and technical advancements have enabled a greater degree of communication and collaboration than ever before. Amongst other things, this has allowed for a particularly interesting triumvirate intersection: • ... -
Combined distributional and logical semantics
(The University of Edinburgh, 2016-06-27)Understanding natural language sentences requires interpreting words, and combining the meanings of words into the meanings of sentences. Despite much work on lexical and compositional semantics individually, existing ... -
Robust representation learning approaches for neural population activity
(The University of Edinburgh, 2023-04-19)Understanding communication patterns between different regions of the human brain is key to learning useful spatial representations. Once learned, these representations present a foundation on which new tasks can be learned ... -
Insect neuroethology of reinforcement learning
(The University of Edinburgh, 2023-03-28)Historically, reinforcement learning is a branch of machine learning founded on observations of how animals learn. This involved collaboration between the fields of biology and artificial intelligence that was beneficial ... -
Planning automated guided vehicle movements in a factory
(The University of Edinburgh, 1988)This dissertation examines the problems of planning automated guided vehicle (AGV) movement schedules in an automated factory. AGVs are used mainly for material delivery and will have an important role in linking "islands ... -
Bayesian scalar-on-image regression via random image partition models: automatic identification of regions of interest
(The University of Edinburgh, 2023-03-21)Scalar-on-image regression aims to investigate changes in a scalar response of interest based on high-dimensional imaging data. These problems are increasingly prevalent in numerous domains, particularly in biomedical ... -
Using local linguistic context for text-to-speech
(The University of Edinburgh, 2023-03-15)Synthetic speech generated by state-of-the-art Text-to-Speech (TTS) models achieves unprecedented levels of naturalness. Training, inference and evaluation of TTS models has consistently been performed on isolated utterances ... -
Spiritual polarisation on social media: the case of Arab atheists on Twitter
(The University of Edinburgh, 2023-02-22)Social media platforms provide an unprecedented method of communication, and they are considered an integral part of people's lifestyles. Also, these platforms facilitate forming communities, groups and networks. Hence, ... -
Use of proxies in designing for and with autistic children: supporting friendship as a case study
(The University of Edinburgh, 2023-02-20)Participatory Design (PD) is an approach for designing new technologies which involves end users in the design process. It is generally accepted that involving users in the design process gives them a sense of ownership ... -
Zero-cost abstractions for irregular data shapes in a high-performance parallel language
(The University of Edinburgh, 2023-02-15)Modern parallel accelerators offer an unprecedented degree of performance, and are used pervasively in important application domains, such as High Performance Computing and Machine Learning. However, these accelerators ... -
Neural distribution estimation as a two-part problem
(The University of Edinburgh, 2023-02-14)Given a dataset of examples, distribution estimation is the task of approximating the assumed underlying probability distribution from which those samples were drawn. Neural distribution estimation relies on the powerful ...