Neural Persistence: A Complexity Measure for Deep Neural Networks Using Algebraic Topology

Im Viewer öffnen
Full text (accepted version)
Download
Full text (accepted version) (PDF, 2.061Mb)
Thumbnail
Open access
Autor(in)
Rieck, Bastian Alexandercc
Togninalli, Matteo
Bock, Christian
Moor, Michael
Horn, Maxcc
Gumbsch, Thomas
Borgwardt, Karsten
Alle anzeigen
Datum
2019-02-22
Typ
  • Conference Paper
Rechte / Lizenz
In Copyright - Non-Commercial Use Permitted
Persistenter Link
https://doi.org/10.3929/ethz-b-000327207
Publikationsstatus
published
Externe Links
https://openreview.net/forum?id=ByxkijC5FQ
Suchen via SFX
Buchtitel
International Conference on Learning Representations (ICLR 2019)
Verlag
OpenReview
Konferenz
7th International Conference on Learning Representations (ICLR 2019), New Orleans, LO, USA, May 6-9, 2019
Thema
Algebraic topology; Persistent homology; Network complexity; Neural network
Organisationseinheit
02060 - Dep. Biosysteme / Dep. of Biosystems Science and Eng.
Zugehörige Publikationen und Daten
Mehr
Alle Metadaten anzeigen
ETH Bibliographie
yes
Altmetrics