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 78 for “"Generative modelling"”.
-
Generative modelling and adversarial learning
… of real-world data, such as natural images. Generative adversarial networks (GAN), which are based on the adversarial learning paradigm, are one of the main types of methods for deriving generative models from complicated real-world data. GAN and its variants use a generator to synthesise …
-
Generative modelling on constrained manifolds
Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-image tasks. Building on this success, diffusion models have recently been extended to the Riemannian manifold setting, …
-
Generative modelling under epistemic uncertainty
… contribution of this work lies in re-imagining Generative AI under epistemic uncertainty. We introduce Random-Set Large Language Models (RS-LLMs), which predict belief functions over token sets to quantify second-order uncertainty, thereby providing a robust mechanism for hallucination …
-
Generative modelling of single-cell microscopy images
Abstract not currently available.
-
Simulation-Based Inference with Modern Generative Modelling
… of machine learning techniques. For example, generative modelling, a related yet distinct topic to likelihood-free inference, is a fast moving and very active area of research, whose ideas have already proved very successful in likelihood-free inference. In lieu of this fact, in this work we …
-
Generative modelling for supervised, unsupervised and private learning
… this thesis we develop several state-of-the-art generative modelling-based approaches for a variety of supervised, unsupervised and private learning problems. In the (almost) supervised domain, we tackle the problems of treatment effect estimation, imputation and feature selection. For treatment …
-
Generative modelling with diffusion models on Riemannian manifolds
Generative modelling is a cornerstone approach of modern deep learning for modelling the distribution of a complex random variable from samples. It has seen applications in a wide range of settings, including the modelling of images, text, and video. Orthogonally, the field of geometric deep …
-
Morphologically Preserving Generative Modelling of the Human Brain
… of modalities. Even so, fully-unsupervised generative modelling of the human brain has not been widely studied with only a handful of models being available namely an Alpha-Wasserstein Generative Adversarial Network (α-WGAN) [97], a Cycle Consistent Embedding GAN (CCE-GAN) [202] and a …
-
Probabilistic models and Monte Carlo objectives in generative modelling
<p>Generative modelling, i.e. learning probability distributions of interest, is a key and challenging problem in statistics and machine learning. With recent breakthroughs in deep learning, there have been remarkable advances in applying novel machine learning methods to solve generative modelling …
-
Generative modelling for improved decision making in data-limited applications
L'abstract è presente nell'allegato / the abstract is in the attachment
-
Generative modelling and transformer-based sequence learning for microbiome analysis
… This thesis investigates recent advances in generative modelling and transformer-based architectures for microbiome analysis, with a focus on improving disease classification and assessing their potential to inform our understanding of the human microbiome. The first chapter provides an …
-
Generative modelling: addressing open problems in model misspecification and differential privacy
<p>Generative modelling has become a popular application of artificial intelligence. Model performance can, however, be impacted negatively when the generative model is misspecified, or when the generative model estimator is modified to adhere to a privacy notion such as differential privacy. In …
-
Controllable Generative Modelling and Diversity Image Restoration for Biomedical Image data
This PhD thesis presents research on fluorescence microscopy employing computer vision techniques and has been submitted to the Faculty of Computer Science at TU Dresden. Fluorescence microscopy is a vital tool in life sciences, enabling visualization of cellular and sub-cellular structures using …
-
Generative modelling and inverse problem solving for networks in hyperbolic space
… The popularity-similarity-optimization (PSO) generative model is able to grow random geometric graphs in the hyperbolic space with realistic properties such as clustering, small-worldness, scale-freeness and rich-clubness. However, it misses to reproduce an important feature of real complex …
-
Enabling Conditional Generation Without Training: Plug & Play Generative Modelling using Diffusion Models
… achieved state-of-the-art results across various generative modeling tasks, including text, image, video, and audio generation. By iteratively refining standard Gaussian noise into structured signals, these models offer remarkable flexibility. However, their practical capabilities remain …
-
Learning the market: machine learning and generative modelling for limit order books
… hardware-accelerated LOB simulation, deep generative modelling of order-flow dynamics, and standardised evaluation of generative market models. Together, these components constitute an end-to-end pipeline for constructing, training, and assessing intelligent agents and generative world …
-
Sound Similarity Measures for Human-Centric Control and Perception in Generative Modelling
The measure of success in generative modelling lies in the similarity between generative<br/>processes learned by models and generative processes existing in the world. This thesis<br/>aims to study how the choice of similarity measures we use in generative modelling<br/>changes the process of …
-
A Theory of Generative Models and Robustness via Regularization
… optimal policies. On the other hand, Generative Adversarial Networks (GANs) employ regularization for computational purposes, avoiding instability in training. Despite the widespread use and multi-faceted motivation of regularization, extensive evidence has suggested that …
-
Generative models for seismic imaging and inversion
Generative modeling, a subfield of deep learning, is emerging as a powerful tool in seismic imaging and inversion. The goal of generative modelling is to approximate intractable probability densities, for example those representing distributions of natural images, with deep neural networks. Given …
-
EVOLUTIONARY OPTIMISATION OF URBAN STREET PATTERNS USING AXIAL LINE ANALYSIS
… line analysis of Space Syntax software with generative modelling to evolve and evaluate a population of urban street patterns through Evolutionary Algorithms. The aim of this dissertation is to assist decision-making in the early "sketch" design of urban street patterns by attempting to use …
Page 1 of 4