Sökning: "Topologisk maskininlärning"

Hittade 4 uppsatser innehållade orden Topologisk maskininlärning.

1. 1. Topological regularization and relative latent representations

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

   Författare :Alejandro García Castellanos; [2023]
   Nyckelord :Algebraic Topology; Large Language Models; Relative Representation; Representation Learning; Model Stitching; Topological DataAnalysis; Zero-shot; Algebraisk topologi; Stora språkmodeller; Relativ representation; Representationsinlärning; Modell sömmar; Topologisk dataanalys; Zero-shot;

   Sammanfattning : This Master's Thesis delves into the application of topological regularization techniques and relative latent representations within the realm of zero-shot model stitching. Building upon the prior work of Moschella et al. 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. Statistical Learning and Analysis on Homology-Based Features

   Master-uppsats, KTH/Matematisk statistik

   Författare :Jens Agerberg; [2020]
   Nyckelord :Applied topology; topological data analysis; TDA; persistent homology; machine learning; Topologisk dataanalys; maskininlärning;

   Sammanfattning : Stable rank has recently been proposed as an invariant to encode the result of persistent homology, a method used in topological data analysis. In this thesis we develop methods for statistical analysis as well as machine learning methods based on stable rank. LÄS MER

5. 4. An Investigation of Neural Network Structure with Topological Data Analysis

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

   Författare :Vladislav Polianskii; [2018]
   Nyckelord :machine learning; deep learning; autoencoders; TDA; computational topology; topological data analysis;

   Sammanfattning : Artificial neural networks at the present time gain notable popularity and show astounding results in many machine learning tasks. This, however, also results in a drawback that the understanding of the processes happening inside of learning algorithms decreases. LÄS MER