Sökning: "Variational problem"

Visar resultat 1 - 5 av 38 uppsatser innehållade orden Variational problem.

1. 1. Modulating Depth Map Features to Estimate 3D Human Pose via Multi-Task Variational Autoencoders

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Kobe Moerman; [2023]
   Nyckelord :3D pose estimation; Joint landmarks; Variational autoencoder; Multi-task model; Loss discrimination; Latent-space modulation; Depth map; 3D-positionsuppskattning; Gemensamma landmärken; Variationell autoencoder; Multitask-modell; Förlustdiskriminering; Latent-space-modulering; Djupkarta;

   Sammanfattning : Human pose estimation (HPE) constitutes a fundamental problem within the domain of computer vision, finding applications in diverse fields like motion analysis and human-computer interaction. This paper introduces innovative methodologies aimed at enhancing the accuracy and robustness of 3D joint estimation. LÄS MER

3. 2. Symmetry in a free boundary problem

   Master-uppsats, KTH/Matematik (Avd.)

   Författare :Seuri Basilio Kuosmanen; [2023]
   Nyckelord :Analysis of PDEs; Bernoulli-type boundary condition; free boundary problem; Laplacian operator; method of moving planes; symmetry; Analys av PDEs; Bernoulli-typ randvärde; frirandsproblem; Laplaceoperatorn; moving-plane metoden; symmetri;

   Sammanfattning : We consider a variational formulation of a Bernoulli-type free boundary problem for the Laplacian operator with discontinuous boundary data. We show the existence of a weak solution to the problem. Moreover, we show that the solution has symmetry properties inherited by symmetric data. LÄS MER

4. 3. Fracture simulation with a hyperelastic phase field model

   Master-uppsats, KTH/Hållfasthetslära

   Författare :Adrien Fradet; [2023]
   Nyckelord :Fracture; Phase field modeling; Hyperelasticity; Brott; fasfält-methoden; hyperelasticite;

   Sammanfattning : The phase field method is a versatile tool to study crack initiation and propagation in systems with complex geometries. Based on a variational formulation of the equilibrium equations, the sharp crack topology is regularized by a crack with diffusive edges and the damage is described by a continuous phase field variable. LÄS MER

5. 4. Solving Partial Differential Equations With Neural Networks

   Master-uppsats, Uppsala universitet/Matematiska institutionen

   Författare :Håkan Karlsson Faronius; [2023]
   Nyckelord :Partial differential equations; neural networks; physics-informed neural networks; deep ritz method; fourier neural operator; importance sampling; inverse problems;

   Sammanfattning : In this thesis three different approaches for solving partial differential equa-tions with neural networks will be explored; namely Physics-Informed NeuralNetworks, Fourier Neural Operators and the Deep Ritz method. Physics-Informed Neural Networks and the Deep Ritz Method are unsupervised machine learning methods, while the Fourier Neural Operator is a supervised method. LÄS MER

7. 5. Sign of the Times : Unmasking Deep Learning for Time Series Anomaly Detection

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Daniel Richards Ravi Arputharaj; [2023]
   Nyckelord :Anomaly detection; multivariate time series data; deep learning models; model complexity; resource-constrained systems; Variational Autoencoders VAEs ; Convolutional Variational Autoencoders; evaluation metrics in time series; Anomalidetektering; Multivariata tidsseriedata; Djupinlärningsmodeller; Modellkomplexitet; Resursbegränsade system; Variational Autoencoders VAEs ; Konvolutionella Variational Autoencoders; Utvärderingsmått inom tidsserier;

   Sammanfattning : Time series anomaly detection has been a longstanding area of research with applications across various domains. In recent years, there has been a surge of interest in applying deep learning models to this problem domain. LÄS MER