Sökning: "Topologisk maskininlärning"
Hittade 4 uppsatser innehållade orden Topologisk maskininlärning.
1. Topological regularization and relative latent representations
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)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
2. Towards topology-aware Variational Auto-Encoders : from InvMap-VAE to Witness Simplicial VAE
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)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
3. Statistical Learning and Analysis on Homology-Based Features
Master-uppsats, KTH/Matematisk statistikSammanfattning : 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
4. An Investigation of Neural Network Structure with Topological Data Analysis
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)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