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 997 for “"generative models"”.
-
Learning Deep Generative Models
… suggest that building such systems requires models with deep architectures that involve many layers of nonlinear processing. The aim of the thesis is to demonstrate that deep generative models that contain many layers of latent variables and millions of parameters can be learned efficiently, …
-
Specification-Guided Generative Models
We introduce Specification-Guided Generative Models (SGMs) - a novel approach to generative models - and illustrate their versatility and effectiveness across various domains. SGMs represent an evolution in model control and expressiveness, providing a framework for augmenting existing models to …
-
Generative models for generic data
Generative models parameterized through large neural networks are now ubiquitous across machine learning. These models are able to generate highly realistic samples, ranging from human-like text to novel chemical compounds. With the ever growing list of potential application areas comes the need to …
-
Towards data efficient generative models
… past decade has seen significant advancements in generative models. As one of the most fundamental machine learning and computer vision tasks, generative models aim to produce realistic-looking synthetic samples by learning from real samples. However, training generative models from scratch …
-
Generative models: theory and applications
… from a data distribution, the central aim of generative modeling is to generate more samples from approximately the same distribution. This framework has recently seen an explosion in popularity, with impressive applications in image generation, language modeling and protein synthesis. The …
-
Generative Models for Computer Vision
… build robust computer vision algorithms, scene models are necessary that are capable of capturing various aspects of the data at the same time. These models should be fairly simple, but capable of adapting to the data. Flexible models, as defined in the machine learning community, are minimally …
-
Exploring knowledge in generative models
Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2024-09-16 without embargo terms
-
Interpretable generative models for precipitation forecasting
… We aimed to enhance the explainability of generative models used in climate science applications, focusing on short to medium-range forecasting. Noticing that several of these models use vision transformer backbones, we adapted an explainability approach initially developed to explore the …
-
Causality : from learning to generative models
… suggest the use of neural networks, specifically generative adversarial networks for learning the causal model when the causal graph is known without latent variables.
-
Learning generative models from corrupted data
… cheap. In the inverse problems literature, generative models are used as unsupervised priors to transform corrupted samples into clean ones. But how can we train these priors in the first place without having access to clean data? In this dissertation, we study the problem of learning …
-
Developmental generative models of brain connectivity
… researchers have developed computational models linking gene expression to brain wiring, often using regression techniques that identify genes implicated in neural development. While these models offer valuable biological insights, they are inherently constrained: they explain connectivity …
-
Causal inference with deep generative models
Estimating causal effects is a fundamental task in causal inference but is fraught with limitations and challenges. Randomised Controlled Trials (RCTs) are considered the gold standard for quantifying the causal effect, but they are often impractical and ethically questionable. Causal effect …
-
Learning factorised representation via generative models.
… irrelevant information from the input. While for generative models, the model can learn a joint distribution over all variables and the latent space can almost maintain the whole information of the dataset rather than task-specific information. But the vanilla generative models can only learn an …
-
Echocardiography generation using deep generative models
… thesis investigates the use of deep generative models to address data scarcity and standardisation challenges in echocardiography. First, a pipeline termed HeartTo Echo is proposed to generate anatomically consistent pseudo-images corresponding to 21 standard TEE views from …
-
Self-Consuming Generative Models Go MAD
Seismic advances in generative AI algorithms for imagery, text, and other data types has led to the temptation to use synthetic data to train next-generation models. Repeating this process creates an autophagous (self-consuming) loop whose properties are poorly understood. We conduct a thorough …
-
Towards Private and Trustworthy Generative Models
The rapid advancement of Generative AI has achieved transformative capabilities, yet it also introduces critical challenges to security and trustworthiness. As these models grow more powerful, ensuring their responsible deployment demands multifaceted solutions. In this proposal, we address three …
Page 1 of 50