Neural embedding: learning the embedding of the manifold of physics data
Abstract In this paper, we present a method of embedding physics data manifolds with metric structure into lower dimensional spaces with simpler metrics, such as Euclidean and Hyperbolic spaces. We then demonstrate that it can be a powerful step in the data anal...
Hoofdauteurs: | Park, Sang E., Harris, Philip, Ostdiek, Bryan |
---|---|
Andere auteurs: | Massachusetts Institute of Technology. Department of Physics |
Formaat: | Artikel |
Taal: | English |
Gepubliceerd in: |
Springer Berlin Heidelberg
2023
|
Online toegang: | https://hdl.handle.net/1721.1/151120 |
Gelijkaardige items
Gelijkaardige items
-
Quasi anomalous knowledge: searching for new physics with embedded knowledge
door: Park, Sang E., et al.
Gepubliceerd in: (2021) -
Quasi anomalous knowledge: searching for new physics with embedded knowledge
door: Park, Sang E., et al.
Gepubliceerd in: (2022) -
Laplacian embedded regression for scalable manifold regularization
door: Chen, Lin, et al.
Gepubliceerd in: (2013) -
Embedding universal covers of graph manifolds in products of trees
door: Hume, D, et al.
Gepubliceerd in: (2013) -
Approximation numbers of Sobolev embeddings of radial functions on isotropic manifolds
door: Leszek Skrzypczak, et al.
Gepubliceerd in: (2007-01-01)