Sökning: "Variational Auto-Encoder"

Visar resultat 6 - 10 av 11 uppsatser innehållade orden Variational Auto-Encoder.

1. 6. Robust Descriptor Learning Using Variational Auto-Encoders

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

   Författare :Leonidas Valavanis; [2020]
   Nyckelord :;

   Sammanfattning : Image matching is the task of finding points in one image corresponding to the same points in the other image. Classical feature descriptors fail to match points when the images are under extreme viewpoint or seasonal changes. This thesis tackles the problem of image matching when two images are under severe changes. LÄS MER

3. 7. Sketch to 3D Model using Generative Query Networks

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

   Författare :Max Nihlén Ramström; [2019]
   Nyckelord :;

   Sammanfattning : For digital artists and animators, translating an idea from a rough sketch to a 3D model is a time consuming process requiring a plethora of different software. In this work, a Generative Model which can directly generate images of 3D models from arbitrary view points by observing sketched 2D images is presented. LÄS MER

4. 8. Modelling user interaction at scale with deep generative methods

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

   Författare :Beatrice Ionascu; [2018]
   Nyckelord :generative model; deep learning; variational auto-encoder; convolutional neural network; time-series; data reconstruction;

   Sammanfattning : Understanding how users interact with a company's service is essential for data-driven businesses that want to better cater to their users and improve their offering. By using a generative machine learning approach it is possible to model user behaviour and generate new data to simulate or recognize and explain typical usage patterns. LÄS MER

5. 9. A Framework for Generative Product Design Powered by Deep Learning and Artificial Intelligence : Applied on Everyday Products

   Master-uppsats, Linköpings universitet/Maskinkonstruktion

   Författare :Alexander Nilsson; Martin Thönners; [2018]
   Nyckelord :Generative Design; Deep Learning; Machine Learning; Artificial Intelligence; Variational Auto Encoder; Generative Adversarial Network; VAE; GAN; Design Variations; Windows; Mullions; Framework; Windows Dataset;

   Sammanfattning : In this master’s thesis we explore the idea of using artificial intelligence in the product design process and seek to develop a conceptual framework for how it can be incorporated to make user customized products more accessible and affordable for everyone. We show how generative deep learning models such as Variational Auto Encoders and Generative Adversarial Networks can be implemented to generate design variations of windows and clarify the general implementation process along with insights from recent research in the field. LÄS MER

7. 10. Augmenting High-Dimensional Data with Deep Generative Models

   Master-uppsats, KTH/Robotik, perception och lärande, RPL

   Författare :Mårten Nilsson; [2018]
   Nyckelord :GAN; GANs; machine learning; deep learning; generative model; generative models; deep generative model; deep generative models; generative adversarial networks; VAE; VAEs; variational autoencoder; variational autoencoders; autoencoder; auto encoder; encoder; decoder; computer vision; eye tracking; pupil localization; pupil; eyes; eye; synthetic data; big data; data generation; synthetic data generation; neural networks; neural network; high-dimensional data; high-resolution images.;

   Sammanfattning : Data augmentation is a technique that can be performed in various ways to improve the training of discriminative models. The recent developments in deep generative models offer new ways of augmenting existing data sets. LÄS MER