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 571 for “"Generative Model"”.
-
Adding prior into generative model
Generative models are developing rapidly. Although many of these models can now produce realistic samples, the finer details often contain unnatural distortions. This issue becomes more pronounced when dealing with data that has fewer training samples but possesses strong structural properties, …
-
A Continuous Space Generative Model
Generative models are a class of machine learning models capable of producing digital images with plausibly realistic properties. They are useful in such applications as visualizing designs, rendering game scenes, and improving images at higher magnifications. Unfortunately, existing generative …
-
Piecewise Diffusive Score-based Generative Model
Diffusion-based generative models have achieved remarkable success across a range of applications. However, their performance often degrades in the presence of imbalanced data. To address this limitation, we introduce a novel generative modeling framework that combines stochastic differential …
-
A generative model for latent position graphs
… there is much to be gained by learning instead a generative model for the underlying random graph distribution. We present a novel neural network-based approach to learning generative models for random graphs. The features used for training are graphlets, subgraph counts of small order, and the …
-
Generative Model Assisted Sampling of Multiscale Dynamical Systems
For complex dynamical systems effectively modeled by either stochastic or deterministic differential equations, sampling the phase space of the system is a crucial modeling step in many applications, from modeling protein folding to the design of a chemical reactor. These problems are often …
-
The meter of Guthlac B: a generative model
… “Iambic Pentameter”). This thesis proposes a model of OE poetic meter based on Hanson and Kiparsky’s parametric theory of universal meter. Hanson and Kiparsky argue that the constituents relevant to meter are not arbitrary or conventional, such as a list of foot or verse types, but are just …
-
A generative model of body ownership and minimal selfhood
… not established a link between neuroanatomical models of the RHI and models of probabilistic information processing in the brain, nor a connection of these models to philosophical accounts of minimal selfhood. The papers presented here were aimed at addressing these issues, via an application of …
-
Unsupervised domain adaptation and generative model for intelligent engineering systems
… of labeled data. However, the discriminative model that is trained using one dataset typically performs poorly when another different but related dataset is applied. In other words, it is difficult to design a discriminative model that can perform consistently well in different application …
-
Efficient and Scalable Generative Model Control for High-Quality Multimodal Synthesis
Generative models, such as diffusion models and generative adversarial networks, have recently transformed foundational image synthesis tasks. However, challenges remain in designing generative models that are best suited for real-world applications and in improving their generalization …
-
Identification of gene modules using a generative model for relational data
This thesis presents generative models for two types of relational data (edge rankings and networks) from block structures, based on Brumm et al (2008). We design and implement a set of inference algorithms, and evaluate them on real as well as simulated data. We conclude with a discussion of how …
-
Complex Dynamics of Contention: Towards a Generative Model of Social Dissent
… social science, namely, the Agent-Based Model (ABM). In addition, both computational modelers and non-modelers have, to this point, ignored important evidence that would shed light on key factors, actors, and mechanisms which may serve as a potential explanandum for social movement …
-
Deep generative model for synthesising and analysing cardiac magnetic resonance images
… and provide variable results. At the same time, generative models have advanced medical image analysis, especially for downstream cardiac image analysis tasks. The aim is to use these synthetic images as viable alternatives to real data in deep learning model training, providing cutting-edge …
-
Whodunit: A Generative Model for Murder Mysteries as an Information Game
This research focuses on creating a model to generate information for a narrative-based game of murder mysteries. The literature review aspect of this research will review previous related research works in the subject of procedural narrative generation, explains the concept information game in the …
-
A sparsity-free compressed sensing theory with applications in generative model recovery
… assuming x admits a certain structure. We model the measurement matrix as M=BA, with arbitrary B∈ℝˡˣᵐ and sub-gaussian A∈ℝᵐˣⁿ; therefore allowing for a family of random measurement matrices which may have heavy tails, dependent rows and columns, and a large dynamic range for the singular …
-
Two Studies of Generative Model Application in Biomedicine and High-Level Synthesis
… ones. We conducted two studies applying deep generative models to solve existing engineering problems: the first involves multi-dimensional, extremely sparse time series forecasting in the intensive care unit (ICU), and the second addresses combinatorial optimization in inverse design for …
-
Enhancing generative model efficiency and control for data generation, reinforcement learning, and robotics
The rapid advancement of generative models has driven their application across a wide range of domains, from image synthesis to complex decision-making systems. This dissertation focuses on enhancing both the efficiency and controllability of generative models, addressing significant challenges …
-
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 …
-
A generative model of tonal tension and its application in dynamic realtime sonification
… presents the design and implementation of a generative model of tonal tension. It further describes the application of the generative model in realtime sonification. The thesis discusses related theoretical work in musical fields including generative system design, sonification, and …
-
The brain as a generative model: information-theoretic surprise in learning and action
… in an internal representation of the world. This generative model is used to perform probabilistic inference, which may be approximated through surprise minimization. This process rests on current beliefs enabling predictions, with expectation violation amounting to surprise. Through repeated …
Page 1 of 29