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 45 for “"deep generative model"”.

  1. Deep generative model for synthesising and analysing cardiac magnetic resonance images

    … of global fatalities. Over the past few decades, deep learning algorithms have increasingly been applied in magnetic resonance imaging (MRI) in the medical field, and in particular, have become central to the diagnosis and prediction of CVDs. However, the dynamic motion of the heart and its …

    whiterose Download PDF for Deep generative model for synthesising and analysing cardiac magnetic resonance images (opens in a new tab)

  2. A WORLD IMAGINED BY AI - GEOSPATIAL DATA QUALITY ENHANCEMENT WITH DEEP GENERATIVE MODEL

    … Data Translation (GDT), a novel unsupervised generative AI framework that resolves this trilemma. GDT learns to translate between different data types to generate new high-fidelity data without needing perfectly matched datasets. Through three studies, the framework generated accurate building …

    nus Repository record for A WORLD IMAGINED BY AI - GEOSPATIAL DATA QUALITY ENHANCEMENT WITH DEEP GENERATIVE MODEL (opens in a new tab) Download file for A WORLD IMAGINED BY AI - GEOSPATIAL DATA QUALITY ENHANCEMENT WITH DEEP GENERATIVE MODEL (opens in a new tab)

  3. Computational approaches to molecular fragment elaboration

    … is likely to bind to a target protein, and in generative algorithms that propose novel high affinity binders in <i>silico</i>.</p> <p>In this thesis, we propose a deep generative model for fragment elaboration for use in fragment-to-lead campaigns. We consider the problem of generating …

    oxford Repository record for Computational approaches to molecular fragment elaboration (opens in a new tab)

  4. Looking deep at people: towards understanding and generating humans in images with deep learning

    … in the field were achieved recently using deep learning. </p> <p>This thesis pursues further advances towards understanding and generating people in visual data by the development of new discriminative and generative deep learning methods. The main contributions are: </p> <p>i) A deep …

    oxford Repository record for Looking deep at people: towards understanding and generating humans in images with deep learning (opens in a new tab)

  5. Towards Uncovering the True Use of Unlabeled Data in Machine Learning

    … data, (ii) whether is possible to scale existing models for positive unlabeled learning, and (iii) whether is possible to train a deep generative model with a single minimization problem.

    trento Repository record for Towards Uncovering the True Use of Unlabeled Data in Machine Learning (opens in a new tab)

  6. Synthesizing a complete tomographic study with nodules from multiple radiograph views via deep generative models

    … density of lung nodules in chest radiographs. A deep generative model, commonly used to synthesize realistic images, can be used to perform 2D to 3D translations. In this thesis, we propose a generative model, optimized using pixel-wise error, that can synthesize a complete tomographic study …

    uiuc Repository record for Synthesizing a complete tomographic study with nodules from multiple radiograph views via deep generative models (opens in a new tab)

  7. Physics-based deep learning for understanding crowd behaviors

    … vehicles, etc. Although numerous excellent models have been proposed for the study of crowd behaviors, challenges persist due to the complexity of human behaviors. This thesis focuses on two primary challenges: crowd dynamics modeling in low-density crowds and physical interaction modeling …

    whiterose Download PDF for Physics-based deep learning for understanding crowd behaviors (opens in a new tab)

  8. Protein-Ligand Binding Affinity Directed Multi-Objective Drug Design Based on Fragment Representation Methods

    … by (1) integrating a graph fragmentation-based deep generative model with a deep evolutionary learning process for large-scale multi-objective molecular optimization, and (2) applying protein-ligand binding affinity scores together with other desired physicochemical properties as objectives. Our …

    brock Repository record for Protein-Ligand Binding Affinity Directed Multi-Objective Drug Design Based on Fragment Representation Methods (opens in a new tab)

  9. Deep Generative Models for Trajectory Prediction and Mobility Network Forecasting

    … we introduce TrajLearn, a Transformer‑based deep generative model that treats trajectories as token sequences and employs spatially constrained beam search to predict each individuals’s next k locations with high precision. Building on these forecasts, we present MobiNetForecast, which …

    york Repository record for Deep Generative Models for Trajectory Prediction and Mobility Network Forecasting (opens in a new tab)

  10. Separating biological processes in single-cell data with deep generative models

    … assumptions. We develop CellUntan- gler, a deep generative model, that addresses batch effects and can embed cells into a flexible latent space composed of multiple subspaces, where each subspace captures a separate biological process. We apply CellUntangler on datasets with only cycling …

    ubc Repository record for Separating biological processes in single-cell data with deep generative models (opens in a new tab) Download PDF for Separating biological processes in single-cell data with deep generative models (opens in a new tab)

  11. Latent Dirichlet transformer VAE for hyperspectral unmixing with bundled endmembers

    … ground-truth data. In this work, we propose a deep generative model and two ”stepping stone” models for hyperspectral unmixing that integrate transformer architectures with variational autoencoders. The proposed approach leverages self-attention mechanisms to capture global spectral–spatial …

    uoit Repository record for Latent Dirichlet transformer VAE for hyperspectral unmixing with bundled endmembers (opens in a new tab)

  12. Data-Efficient Deep Representation Learning for Brain-Computer Interface and Its Applications

    … data-efficient BCI systems by developing robust deep representation learning paradigms. First, we present a comprehensive introduction of BCI systems including the deep learning models, state-of-the-art studies adopting deep learning for BCI drawbacks, and the appealing real-world BCI …

    unsw Repository record for Data-Efficient Deep Representation Learning for Brain-Computer Interface and Its Applications (opens in a new tab)

  13. Towards molecular design with desired property profiles and 3D conformer generation using Deep Generative Models

    … of the vast chemical space. Whilst string based generative models have been thoroughly studied, there has not been yet a great focus on taking into account either the molecular graph or its 3D structure. That is why we propose two generative models: on the one hand, a graph-based deep generative …

    chalmers Repository record for Towards molecular design with desired property profiles and 3D conformer generation using Deep Generative Models (opens in a new tab)

  14. Learning distributions with Particle Mirror Descent

    … By marrying Bayesian probabilistic inference and deep neural networks, deep generative networks have shown remarkable success in various kinds of generative tasks. However, such models usually make an assumption that posterior distribution can be simply characterized as a Gaussian distribution, …

    uiuc Repository record for Learning distributions with Particle Mirror Descent (opens in a new tab)

  15. Deep learning based automated latent fingerprint identification

    … latent fingerprint identification based on deep learning, including fingerprint orientation field construction and matching, latent fingerprint segmentation, latent fingerprint enhancement and latent fingerprint recognition. The main contributions of this thesis are summarized as follows. 1. …

    unsw Repository record for Deep learning based automated latent fingerprint identification (opens in a new tab)

  16. Data Science-Driven Crowd Intelligence and Its Business Applications

    … use data science-driven approaches that leverage deep learning techniques, Bayesian graphical models, and their combinations, to address these concerns. Three essays are included in this dissertation. The first essay designs an interactive attention-based deep learning approach to extract crowd …

    arizona-thes Repository record for Data Science-Driven Crowd Intelligence and Its Business Applications (opens in a new tab)

  17. Applications of time-series generative models and inference techniques

    <p>In this dissertation, we apply deep generative modelling, amortised inference and reinforcement learning methods to real-world, practical phenomenon, and we ask if these techniques can be used to predict complex system dynamics, model biologically plausible behaviour, and guide decision making. …

    oxford Repository record for Applications of time-series generative models and inference techniques (opens in a new tab)

  18. 4D VISION: REPRESENT, RECONSTRUCT AND GENERATE THE DYNAMIC 3D WORLD

    … primarily focused on 2D or static 3D problems, modeling the dynamic 3D world is essential for applications such as embodied robotics, XR/AR devices, and next-generation AI systems operating in time-varying environments. The thesis addresses three fundamental questions: representation (how to …

    penn Repository record for 4D VISION: REPRESENT, RECONSTRUCT AND GENERATE THE DYNAMIC 3D WORLD (opens in a new tab)

  19. Deep visual generation for automotive design upgrading and market optimising

    … Recently, researchers have attempted to apply deep learning, especially deep generative models, to automotive exterior design, which has enabled machines to deliver diverse novel designs from large-scale data. In this thesis, we argue that recent advancements in deep learning techniques, …

    glasgow Repository record for Deep visual generation for automotive design upgrading and market optimising (opens in a new tab) Download PDF for Deep visual generation for automotive design upgrading and market optimising (opens in a new tab)

  20. Circumventing Drug Resistance by Molecular Design: Exact Combinatorial Optimization and Deep Generative Models

    … pathway activation in molecular networks through deep generative models. The energy landscape theorem for protein folding is the main principle utilized for overcoming mutational resistance in a single protein target. iCFN, an exact multistate protein design, has been developed through …

    tamu Repository record for Circumventing Drug Resistance by Molecular Design: Exact Combinatorial Optimization and Deep Generative Models (opens in a new tab)

Page 1 of 3