Sökning: "Variations autokodare"

Hittade 4 uppsatser innehållade orden Variations autokodare.

1. 1. Distance preserving Fermat VAE

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

   Författare :Miklovana Tuci; [2022]
   Nyckelord :;

   Sammanfattning : Deep neural networks takes their strength in the representations, or features, that they internally build. While these internal encodings help networks performing classification or regression tasks on specific data types, it exists a branch of machine learning that has for only purpose to build these representations. LÄS MER

3. 2. Towards topology-aware Variational Auto-Encoders : from InvMap-VAE to Witness Simplicial VAE

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

   Författare :Aniss Aiman Medbouhi; [2022]
   Nyckelord :Variational Auto-Encoder; Nonlinear dimensionality reduction; Generative model; Inverse projection; Computational topology; Algorithmic topology; Topological Data Analysis; Data visualisation; Unsupervised representation learning; Topological machine learning; Betti number; Simplicial complex; Witness complex; Simplicial map; Simplicial regularization.; Variations autokodare; Ickelinjär dimensionalitetsreducering; Generativ modell; Invers projektion; Beräkningstopologi; Algoritmisk topologi; Topologisk Data Analys; Datavisualisering; Oövervakat representationsinlärning; Topologisk maskininlärning; Betti-nummer; Simplicielt komplex; Vittneskomplex; Simpliciel avbildning; Simpliciel regularisering.;

   Sammanfattning : Variational Auto-Encoders (VAEs) are one of the most famous deep generative models. After showing that standard VAEs may not preserve the topology, that is the shape of the data, between the input and the latent space, we tried to modify them so that the topology is preserved. LÄS MER

4. 3. 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

5. 4. Designing Variational Autoencoders for Image Retrieval

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

   Författare :Sara Torres Fernandez; [2018]
   Nyckelord :;

   Sammanfattning : The explosive growth of acquired visual data on the Internet has raised interestin developing advanced image retrieval systems. The main problem relies on thesearch of a specic image among large collections or databases, and this issue isshared by lots of users from a variety of domains, like crime prevention, medicineor journalism. LÄS MER