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"”.

  1. 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 …

    birmingham Download PDF for Unsupervised deep learning for removing structured noise in microscopy and flow cytometry (opens in a new tab)

  2. 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 …

    birmingham Download PDF for Computational complexity perspective on graphical calculi for quantum computation (opens in a new tab)

  3. 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. …

    birmingham Download PDF for The Relevance Score: a landmark-like heuristic for automated planning (opens in a new tab)

  4. 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 …

    birmingham Download PDF for Quantifying the uncertainty and generalisability of machine learning-based virtual staining for high-throughput screening (opens in a new tab)

  5. 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 …

    birmingham Download PDF for Constructive and predicative locale theory in univalent foundations (opens in a new tab)

  6. 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, …

    birmingham Download PDF for Visual object detection and pose estimation of texture-less objects in unstructured environments (opens in a new tab)

  7. 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 …

    birmingham Download PDF for Gaze-controllable face generation (opens in a new tab)

  8. 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 …

    birmingham Download PDF for Recursive optimization: exact and efficient combinatorial optimization algorithm design principles with applications to machine learning (opens in a new tab)

  9. 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 …

    birmingham Download PDF for Graph representation learning: algorithm development and its application to early drug discovery (opens in a new tab)

  10. 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 …

    birmingham Download PDF for Class imbalance in Federated Learning (opens in a new tab)

  11. 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 …

    birmingham Download PDF for Back to Beck: the state monad and the continuation monad from the viewpoint of monadicity (opens in a new tab)

  12. 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 …

    birmingham Download PDF for 3D Pose and shape estimation of hands and manipulated objects from images and videos (opens in a new tab)

  13. 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 …

    birmingham Download PDF for Advancing optimization and evaluation for dynamic capacitated arc routing problems (opens in a new tab)

  14. 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, …

    birmingham Download PDF for Advancing multi-domain active learning: strategies and techniques using neural networks for classification (opens in a new tab)

  15. 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 …

    birmingham Download PDF for Improving the interpretability of machine learning approaches with user-generated data (opens in a new tab)

  16. 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 …

    birmingham Download PDF for Authentication with what you have: improving resilience and usability (opens in a new tab)

  17. 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 …

    birmingham Download PDF for Blind source separation of hard clipped audio mixtures (opens in a new tab)

  18. 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 …

    birmingham Download PDF for Surrogate-assisted evolutionary algorithms for computationally expensive optimisation problems (opens in a new tab)

  19. 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 …

    birmingham Download PDF for Dynamic multi-objective optimization using evolutionary algorithms (opens in a new tab)

  20. 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 …

    birmingham Download PDF for Enhancing word representations for emotional intensity and offensive language detection in Arabic microblog text (opens in a new tab)

Page 1 of 70