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 21 for “"VAEs"”.
-
Approximate Inference in Variational Autoencoders
… and interpretations of approximate inference in VAEs. This thesis reviews many of the recent developments made to improve VAEs. One such improvement is the importance-weighted autoencoder. The standard interpretation of importance-weighted autoencoders is that they maximize a tighter lower bound …
-
Variational Autoencoders for Discovering Influential Latent Factors
… data. In this vein, variational autoencoders (VAEs) and their variants are one technique of generative modeling (and therefore representation learning) using variational inference under the assumption that the underlying data distribution is composed of a few latent random variables. For …
-
Efficient Gaussian Random Number Generators in HLS4ML
… networks, such as Variational Autoencoders (VAEs), often relies on FPGAs for their balance of performance and energy efficiency. VAEs require accurate Gaussian distributions for latent space sampling, but traditional methods like the Central Limit Theorem (CLT) are resource-intensive. The …
-
Using generative modelling in healthcare
… models, namely Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs) and their variants. Subsequently, we shall review some new developed imputation methods which are based on GANs and VAEs. We shall assess their performance under various missingness scenarios via …
-
Non-linear Multi Omics Data Integration Method Using Conditional Variational Autoencoders
… techniques that use Variational Autoencoders (VAEs) for data integration. Similarly, Zarayeneh et al., 2017 proposed a method called the Integrative Gene Regulatory Network (iGRN), which combines multiple layers of omics data using a network made up entirely of gene nodes. This thesis focuses …
-
JoVA-hinge: joint variational autoencoders for personalized recommendation with implicit feedback
Recently, Variational Autoencoders (VAEs) have shown remarkable performance in collaborative filtering (CF) with implicit feedback. These existing recommendation models learn user representations to reconstruct or predict user preferences. However, existing VAE-based recommendation models learn …
-
Modelling non-linearity in 3D shapes: A comparative study of Gaussian process morphable models and variational autoencoders for 3D shape data
… relative generalisation performance compared to VAEs, in the presence of non-linear shape variation by at least a factor of six. However, the non-linear VAEs, despite the simplistic training scheme, presented improved specificity generative performance of at least 18% for both datasets.
-
Relaxing assumptions in deep probabilistic modelling
… of latent space constraints. JSGα-VAEs lead to better reconstruction and generation when compared to baseline VAEs and utilise a single hyperparameter which can be easily interpreted in latent space. Secondly, heavy-tailed denoising score matching (HTDSM) is proposed, motivated by …
-
Using heterogeneous Graph Neural Networks(hGNN) to predict cell-cell communication
… Learning, and Variational Autoencoders (VAEs) across multiple datasets. Our study compares these methods and establishes benchmarks for assessing their effectiveness beyond traditional case studies. By integrating extensive signaling pathway data, we aim to unveil complex cell-cell …
-
AI-Assisted Pipeline for 3D Face Avatar Generation
… Networks (GANs) and Variational Auto-Encoders (VAEs) to automate avatar creation. Our pipeline offers control over three aspects: face shape, skin color, and fine details like beards or wrinkles. This provides artists flexibility in avatar creation and can integrate with tools like MOSAR for …
-
Generative models for predictive UI design tools
… (GANs) [7] and variational auto-encoders (VAEs) [15]. We train the GAN and VAE models over 1949 mobile UIs that represent a variety of screen types (e.g. Login, Onboarding), and compare both models along standard and design-based metrics, identifying key tradeoffs. Finally, we present a …
-
Using Deep Learning to Extract Multicellular Aggregation Features of Myxococcus xanthus
… and StyleGAN2 into a Variational AutoEncoders (VAEs), and using Siamese architectures as the similarity metric. This pipeline transforms high-resolution microscopy data into low-dimensional phenotypic feature vectors. Human evaluations confirmed the model captures phenotypic diversity, enabling …
-
Exploration of the mouse osteoblast transcriptome
Contains fulltext : 30023.pdf (Publisher’s version ) (Open Access)
-
On Impact of Network Architecture for Deep Learning
… NLP, we address the training deficiency of text VAEs with autoregressive decoders through two approaches. First, we introduce a cyclical annealing schedule that enables progressive learning of meaningful latent codes by leveraginginformative representations from previous cycles as warm restarts. …
-
Machine learning for cryo-EM structure determination
… states. Variational auto-encoders (VAEs) have recently been applied to disentangle these conformations by encoding maps into a low-dimensional latent space. As an additional part of my doctoral work, in a collaboration with Dari Kimanius, I developed a VAE with a novel decoder …
-
Injecting Inductive Biases into Distributed Representations of Text
… these properties with Variational Autoencoders (VAEs). First, we regulate the amount of information encoded in a sentence embedding via constraint optimisation of a VAE objective function. We show that increasing amount of information allows to better discriminate sentences. Afterwards, to impose …
-
Ambient seismic noise tomography of the southern United States and seismic inversion with dictionary learning using unsupervised machine learning.
… training. We also use Variational Autoencoders (VAEs) for efficient high-frequency reflectivity recovery. Seismic examples validate our approach.
-
Topics in Deep Generative Modelling Mathematical and Computational Aspects of Diffusion Models and Generative Adversarial Networks
… diffusion models with variational autoencoders (VAEs). This hybrid model can be perceived as either an enhanced VAE with a diffusion-based decoder or a method to derive a latent space from a pre-trained diffusion model. The thesis also critically evaluates the existing theory behind Wasserstein …
-
Deep Learning Methods for Built Environment Operational Management
… architectures, including Autoencoders (AEs and VAEs) and GANs. Using this framework, 14 combinations of data embedding techniques (ensemble, reshaping, stacking, TS-to-image conversion) and model types (1D and 2D DL models) were evaluated. Using multi-channel railroad track inspection data, a 2D …
Page 1 of 2