Learning with Known Operators reduces Maximum Training Error Bounds

We describe an approach for incorporating prior knowledge into machine learning algorithms. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the algorithm. Any operation that allows computation of a gradient or sub-gradient toward...

Descripción completa

Detalles Bibliográficos
Autores principales: Maier, Andreas K., Syben, Christopher, Stimpel, Bernhard, Würfl, Tobias, Hoffmann, Mathis, Schebesch, Frank, Fu, Weilin, Mill, Leonid, Kling, Lasse, Christiansen, Silke
Formato: Online Artículo Texto
Lenguaje:English
Publicado: 2019
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6690833/
https://www.ncbi.nlm.nih.gov/pubmed/31406960
http://dx.doi.org/10.1038/s42256-019-0077-5

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6690833/
https://www.ncbi.nlm.nih.gov/pubmed/31406960
http://dx.doi.org/10.1038/s42256-019-0077-5

Ejemplares similares