205K - views

Provable Bounds for Learning Some Deep Representations Sanjeev Arora ARORA CS PRINCETON EDU Princeton University Computer Science Department and Center for Computational Intractability Princeton USA

Our gen erative model is an node multilayer network that has degree at most for some 947 and each edge has a random edge weight in 1 Our algorithm learns almost all networks in this class with polynomial running time The sample complexity is quadra

Tags : Our gen erative model
Embed :
Pdf Download Link

Download Pdf - The PPT/PDF document "Provable Bounds for Learning Some Deep R..." is the property of its rightful owner. Permission is granted to download and print the materials on this web site for personal, non-commercial use only, and to display it on your personal computer provided you do not modify the materials and that you retain all copyright notices contained in the materials. By downloading content from our website, you accept the terms of this agreement.

Provable Bounds for Learning Some Deep Representations Sanjeev Arora ARORA CS PRINCETON EDU Princeton University Computer Science Department and Center for Computational Intractability Princeton USA






Presentation on theme: "Provable Bounds for Learning Some Deep Representations Sanjeev Arora ARORA CS PRINCETON EDU Princeton University Computer Science Department and Center for Computational Intractability Princeton USA "— Presentation transcript: