Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 1383 for “"QA75 Electronic computers. Computer science"”.
-
Unsupervised deep learning for removing structured noise in microscopy and flow cytometry
Microscopy and flow cytometry are pillars of life science research. They use agents such as light or electrons to analyse the structure and composition of biological samples at micrometre and nanometre scales. However, the samples can be damaged by this very process, resulting in observations that …
-
Computational complexity perspective on graphical calculi for quantum computation
… quantum computing. However, physical quantum computers do not understand diagrams and require explicit quantum circuits as inputs. Finding a circuit equivalent to the given diagram is known as circuit extraction. Such problems in graphical calculi form a limitation preventing the wider …
-
The Relevance Score: a landmark-like heuristic for automated planning
Landmarks are facts or actions that appear in all valid solutions of a planning problem. They have been used successfully to calculate heuristics that guide the search for a plan. The potential uses for landmarks are limited by their definition relying on the existence of at least one valid plan. …
-
Quantifying the uncertainty and generalisability of machine learning-based virtual staining for high-throughput screening
High-throughput screening (HTS) [1] with fluorescence microscopy [2] enables different biological structures within cells to be simultaneously revealed, at scale, so that drug compound effects can be quantified. Fluorescence microscopy, however, is expensive, time-consuming [3] and can negatively …
-
Constructive and predicative locale theory in univalent foundations
… or any form of the limited principle of omniscience. In the context of univalent foundations, predicativity refers specifically to the development of mathematics without the use of Voevodsky’s propositional resizing axioms. The traditional approach to the predicative development of point-free …
-
Visual object detection and pose estimation of texture-less objects in unstructured environments
Advancements in industries such as manufacturing, logistics, healthcare, and energy increasingly rely on autonomous robots to enhance reliability, efficiency, and safety. A critical factor in these advancements is the ability of these robots to accurately perceive and understand their environments, …
-
Gaze-controllable face generation
… such as virtual reality, digital humans, and computer-generated filmmaking. Traditional methods achieve gaze control through image replacement or graphical modeling techniques. However, to make gaze-controllable face generation more accessible and practical, researchers are increasingly …
-
Recursive optimization: exact and efficient combinatorial optimization algorithm design principles with applications to machine learning
This thesis presents a generic algorithm design framework for solving combinatorial optimization problems, it subsumes the classical recursive optimization methods, such as greedy, dynamic programming, divide-and-conquer, and branch-and-bound (BnB) methods. In particular, this thesis focuses on …
-
Graph representation learning: algorithm development and its application to early drug discovery
Drug discovery is a time- and cost-consuming process because of the complex biological mechanisms of the diseases and interactions between the drug and biological system. In the early (candidate selection) stage of drug discovery, machine learning, especially the graph representation learning …
-
Class imbalance in Federated Learning
Federated Learning (FL) is a distributed and privacy protected machine learning paradigm that trains a global model across multiple clients without gathering their local data. Class imbalance is a common issue in machine learning, where the number of samples in each class is not balanced. In the …
-
Back to Beck: the state monad and the continuation monad from the viewpoint of monadicity
We introduce control algebras, which are algebras of two operations called call/cc and abort. The two operations are natural ones among programs that manipulate their plan of work. The significance of the formulation is that it is operationally natural, yet the notion of algebras is equivalent to …
-
3D Pose and shape estimation of hands and manipulated objects from images and videos
… is an important and long-standing problem in computer vision. This problem can be particularly challenging due to extreme variations in object shape and texture. In addition, heavy occlusions can be introduced by other objects in the scene or humans during interaction. Nevertheless, modeling …
-
Advancing optimization and evaluation for dynamic capacitated arc routing problems
The Capacitated Arc Routing Problem (CARP) is a challenging combinatorial optimization problem abstracted from real-world applications, such as waste collection and road gritting. It aims at scheduling a fleet of vehicles, each with a limited capacity, to serve a series of tasks in a graph spending …
-
Advancing multi-domain active learning: strategies and techniques using neural networks for classification
Dealing with data collected from various domains has emerged as a pervasive challenge in machine learning applications, necessitating the use of multi-domain learning (MDL) to efficiently process and learn from the collected multi-domain data, which have different distributions. Nevertheless, …
-
Improving the interpretability of machine learning approaches with user-generated data
Given the increasing deployment of automatic decision systems in many critical scenarios, understanding and explaining machine-based decision systems has become an important problem to be solved. For this reason, recently, there has been an increasing interest in what we commonly call Explainable …
-
Authentication with what you have: improving resilience and usability
This thesis aims to improve the resilience and usability of authentication with what you have. I identify two problems which are pertinent to this area and present solutions to each. The first problem concerns the remote registration of multiple authenticators. User authentication with discrete …
-
Blind source separation of hard clipped audio mixtures
Blind source separation of hard-clipped audio mixtures is a challenging problem. This thesis presents a novel approach to recovering sources from mixtures affected by hard clipping distortion. This approach relies on making geometric observations about the nature of clipped mixtures. An assumption …
-
Surrogate-assisted evolutionary algorithms for computationally expensive optimisation problems
Surrogate-assisted evolutionary algorithms (SAEAs) are designed to solve black-box optimisation problems that are computationally expensive. These optimisation problems could be multi-objective or/and constrained. In industry, many real-world optimisation problems, such as engine calibration …
-
Dynamic multi-objective optimization using evolutionary algorithms
Dynamic Multi-objective Optimization Problems (DMOPs) offer an opportunity to examine and solve challenging real world scenarios where trade-off solutions between conflicting objectives change over time. Definition of benchmark problems allows modelling of industry scenarios across transport, power …
-
Enhancing word representations for emotional intensity and offensive language detection in Arabic microblog text
Social media motivates people to express their emotions and share them publicly. However, at the same time, there are those who use it to spread racism and offensive language. Detecting emotional intensity and offensive language can be challenging in the context of social media microblogs, such as …
Page 1 of 70