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 Encoder"”.
-
Towards Learning the Geometry of Data: From Diffusion Models to Riemannian Geometry
… 6, we introduce ScoreVAE, a novel Variational Auto-encoder (VAE) that alleviates the typical VAE limitation of blurry reconstructions by combining a frozen pretrained diffusion model with a learnable time-dependent encoder to model the reconstruction distribution. In chapter 5, we establish the …
-
Topic Modeling for Inferring Brain States from Electroencephalography (EEG) Signals
… present an architecture of a deep convolutional auto-encoder neural network to automatically learn feature representations from EEG signals. The network uses a combination of convolutional and max-pooling layers to achieve reduction in the dimensionality of raw data, and can be trained in an …
-
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 …
-
Object discovery via layer disposal
… We capitalize on this signal to develop an auto-encoder that decomposes an image into layers, and when all layers are combined, it reconstructs the input image. However, when a layer is removed, the model learns to produce a different image that still looks natural to an adversary, which is …
-
Learning distributions with Particle Mirror Descent
… posterior, we introduce a variant of Variational Auto-encoder model that uses a mixture of customized kernels as posterior distribution in latent space. Our deep generative model produces visually plausible images as well as good clustering performance using latent representations.
-
Post-processing Techniques for Word Embedding
… datasets. We propose a novel method Orthogonal Auto Encoder with Variational Dropout (OAEVD), which utilizes orthogonal autoencoders and variational dropout techniques to enhance word embedding. The orthogonality constraint encourages more diversity in the latent space, and variational dropout …
-
Unsupervised Machine Learning Application for the Identification of Kimberlite Ore Facie using Convolutional Neural Networks and Deep Embedded Clustering
… types or facie using features developed from the auto-encoder portion of the ConvDEC-DA modelling. While this research focuses on the clustering of Kimberlite rocks according to their respective facie, similar implementations are possible for a wide range of mining and rock types.
-
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 …
-
Deep learning for processing histopathology images
… on pathologists, there is a growing need for automated image analysis pipelines that are able to filter out obviously benign samples. However, these algorithms are sensitive to factors of variation such as the staining and scanning conditions with which a tissue specimen is processed that …
-
Vision-based 6D object pose estimation for robot manipulation
… In particular, we propose a category-level auto-encoder network for depth measurements so that the feature embeddings are independent of the object instances. We extend the states in the PoseRBPF to handle the objects in different sizes. We evaluate our tracking framework on a category-level …
-
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 …
-
Tecniche di Machine Learning per Applicazione in Reti prive di Infrastruttura
… e localizzata. Gli algoritmi di apprendimento automatico potrebbero svolgere un ruolo importante nel fornire comunicazioni e gestione delle risorse affidabili ed efficienti dal punto di vista energetico; in effetti può essere utile nella gestione dei grandi volumi di calcolo e comunicazione …
-
Reduced order modeling of convection-dominated flows, dimensionality reduction and stabilization
… convection dominated flows. We design a low-rank auto-encoder to specifically reduce the dimensionality of solution arising from convection-dominated nonlinear physical systems. Although existing nonlinear manifold learning methods seem to be compelling tools to reduce the dimensionality of data …
-
Deep reinforcement learning for adaptive monitarizacion and patrolling of water resources with unmanned surface vehicles
… human efforts and high costs. The use of autonomous surface vehicles equipped with water quality measurement equipment and pollution variables increases efficiency and improves the precision and validity of biological models for such resources. Deploying these vehicles requires special …
-
Learning and evaluating image representations
… a LEARCH-based model more recent work builds on auto-encoder representations. For authoring decompositions and removing rain, cracks, and glare, autoencoder models are learned from fake data and then shown to be applicable on real images. For learning to decompose rainy images cycle consistency …
-
Energy disaggregation techniques for visualization and improvement of energy efficiency in processes and buildings
… buildings. A novel Fully-Convolutional denoising Auto-Encoder (FCN-dAE) model is proposed for NILM in large buildings, which outperforms the state-of-art NILM approaches on data from the hospital, and shows better computational efficiency than the previous models in terms of number trainable …
-
Cold-start universal information extraction
… the desire to endow machines with the ability to automatically extract, assess, and understand text in order to answer these fundamental questions. IE has been serving as one of the most important components for many downstream natural language processing (NLP) tasks, such as knowledge base …
-
Advancing semantic modeling: addressing coordination, interpretability, and data scarcity in domain representation
… leverages large language models and prefix-tuned autoencoders to enrich sparse inputs and produce coherent topics under extreme document-level scarcity. Low-Resource Topic Modeling (LRTM) presents DALTA, a domain-adaptation framework that transfers knowledge from data-rich corpora while preserving …
-
Learning for Visual Synthesis and Transformation
… model that consists of three modules: an encoder, a gated transformer, and a decoder. Different styles can be achieved through different branches of gated transformers while the encoder and decoder are used for capturing structure information sharing weights for all styles. A …
-
Applications of Probabilistic Machine Learning Models to Semiconductor Fabrication
… support vector machines, as well as variational auto encoder based anomaly detection methods. Finally, we investigate the use of Bayesian optimization and Gaussian process models to improve thickness uniformity in sputtering deposition processes. Here, we use Gaussian processes to model the …
Page 1 of 2