Iskalni niz:
išči po
išči po
išči po
išči po
Vrsta gradiva:
Jezik:
Št. zadetkov: 2
How Can Deep Rectifier Networks Achieve Linear Separability and Preserve Distances?
Senjian An
Video in druga učna gradiva
Oznake: computer science;machine learning
This paper investigates how hidden layers of deep rectifier networks are capable of transforming two or more pattern sets to be linearly separable while preserving the distances with a guaranteed degree, and proves the universal classification power of such distance preserving rectifier networks. Th ...
Leto: 2015 Vir: videolectures.net
Poster Spotlights
Senjian An , Gabriel Takacs , Minh-Tri Pham , Alexander Toshev , Xavier Perrotton , Richard Socher , Worapan Kusakunniran , Markus Enzweiler , Bertram Drost , Sudheendra Vijayanarasimhan , Timothee Cour , Christoph Lampert , Stefan Walk , Michael Alejandro Villamizar Vergel , David Aldavert , Oisin Mac Aodha , Leo Zhu , Olga Russakovsky , Piotr Dollár , Zhiqi Zhang , Josip Krapac
Video in druga učna gradiva
Oznake: computer science;natural language processing;computer vision;object recognition
Leto: 2010 Vir: videolectures.net
Št. zadetkov: 2
Ključne besede:
Leto izdaje:
Repozitorij:
Tipologija:
Jezik: