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 23 for “"Auto encoders"”.
-
End-to-end non-negative auto-encoders: a deep neural alternative to non-negative audio modeling
… investigate the idea of end-to-end non-negative autoencoders (NAEs) as an updated deep learning based alternative framework to non-negative audio modeling. We show that end-to-end NAEs combine the modeling advantages of non-negative matrix factorization and the generalizability of neural networks …
-
Deep Generative Models and Biological Applications
… </p><p>The recent proposed Variational auto-encoders (VAE) framework is an efficient high-dimensional inference method to modeling complicated data manifold in an approximate Bayesian way, i.e., variational inference. </p><p>We first discuss how to design fast stochastic backpropagation …
-
Automated Ligand Design in Simulated Molecular Docking - Optimising ligand binding affinity through the application of deep Q-learning to docking simulations
… with machine learning algorithms that can automatically design novel ligands for biological targets. Recent work has demonstrated the viability of deep reinforcement learning, generative adversarial networks and auto-encoders. Here, we extend state-of-the-art deep reinforcement learning …
-
AI-Assisted Pipeline for 3D Face Avatar Generation
… Adversarial 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 …
-
Three ploys for robust co-generation with generative adversarial nets
… adversarial nets (GANs) and variational auto-encoders enable accurate modeling of high-dimensional data distributions by forward propagating a sample drawn from a latent space. However, an often overlooked shortcoming is their inability to find an arbitrary marginal distribution, which is …
-
Neural network libor market model for pricing and hedging interest rate derivatives
… will introduce a new formulation of variational auto-encoders in order to generate the data we require. Our variational auto-encoder is based on data generation principles from elementary probability i.e. finding the inverse cumulative distribution function and using uniform inputs to generate …
-
Automatically extracting interaction and app data from mobile application traces
… in an unsupervised manner using neural network auto-encoders and k-means clustering. The research work also enables us to find similar layouts across apps and make claims about the location of some of these interactive elements. This research provides a scalable data-driven approach to finding …
-
Generative models for predictive UI design tools
… be used queried multiple times in succession to autocomplete an entire UI screen. To power this design interaction, we present two types of models: generative adversarial networks (GANs) [7] and variational auto-encoders (VAEs) [15]. We train the GAN and VAE models over 1949 mobile UIs that …
-
Comparative Study of Dimension Reduction Approaches With Respect to Visualization in 3-Dimensional Space
… DBN (Deep Belief Networks) and Stacked Auto-encoders. This thesis is intended to ultimately show which technique performs best for dimension reduction with the help of studied experiments.</p>
-
3D Hand Pose Estimation Via a Lightweight Deep Learning Model
… of hands in the image, (2) sparse adversarial auto-encoders trained on hand RGB images, and (3) adversarial auto-encoder for capturing 3D hand pose distributions. Finally, the proposed model yielded the accuracy comparable to state-of-the-art 3D hand pose estimation. However, our model is much …
-
Machine learning for cryo-EM structure determination
… My doctoral work focused on ModelAngelo, an automated model-building and protein-identification program for cryo-EM. I designed specialised graph-neural-network architectures that allow ModelAngelo to build atomic models in high-resolution maps with accuracy matching that of human experts. I …
-
Toward more scalable structured models
… distributions in Variational and Wasserstein auto-encoders.
-
Parametric PAINTOVER: Generating Design Models via Image Encoders and Latent Trajectories
… We propose latent spaces of large pre-trained auto-encoders as shared, design spaces for translating states of design among mediums and dimensions. We implement rendering and image encoding to use images as an interface among the outputs and inputs of the model, enabling users with direct …
-
Perturbation Modeling for Molecular Design of Protein Tyrosine Kinase Inhibitors using Unsupervised Machine Learning
… generative learning technique called Variational Auto-Encoders and Unsupervised Machine Learning techniques. This study focuses specifically using the methods above to transform molecules from various kinase inhibitor families to SRC Kinase Inhibitors. These generated molecules are evaluated using …
-
Generative modeling of sequential data
… (unlike popular methods such as variational autoencoders or generative adversarial networks) significantly enhances the generative model learning performance, as evidenced by the experiments we conduct on handwritten digit dataset (MNIST) and celebrity faces dataset (CELEB-A). -We prove that …
-
Learning joint latent representations for images and language
… captioning problem using conditional variational auto-encoders (CVAEs). Standard CVAEs with a fixed Gaussian prior yield descriptions with too little variability. Instead, we propose two models that explicitly structure the latent space with K components corresponding to different types of image …
-
Development of Surrogate Model for FEM Error Prediction using Deep Learning
… dataset of 12,000 images consists of three auto encoders, one encoder-decoder assembly, and two multi-output regression neural networks. With the error of less than 1% in the neural network training shows good memorization and generalization performance. Our final surrogate model takes 15.5 …
-
Unsupervised Learning : Model-guided and Model-agnostic Approaches
… to cluster diverse types of data. Even though auto-encoders had been used for clustering in the past, clustering using GANs was unexplored prior to this work. ClusterGAN modifies the vanilla GAN architecture to enable embedding of data in the latent space where cluster structure is revealed. It …
-
Learning multiple solutions to computer vision problems
… therefore we also develop a method that uses automatically generated (or learned) latent proposals. Our latent proposal method uses a combination of variational auto-encoders [30] and mixture density net- works [31] to perform multiple colorization. To the best of our knowledge, this is the …
-
Computational Augmentation of Model Based System Engineering: Supporting Mechatronic System Model Development with AI Technologies
Efforts in applying computational support for automatic design synthesis and configuration generation as well as efforts to support descriptive and computational model development for system design and verification has been approached with semantic formalisation of modelling languages and of …
Page 1 of 2