203K - views

Lecture Notes Some notes on gradient descent Marc Toussaint Machine Learning Robotics lab FU Berlin Arnimallee Berlin Germany May Ill briey cover the following topics about gradient de scent Ste

This leads to methods for stepsize adaptation How to guarantee monotonous convergence Reconsideration of what steepest descent should mean in the case of a nonEuclidean metric This leads to the socalled covariant or natural gradient A brief comment

Tags : This leads methods
Embed :
Pdf Download Link

Download Pdf - The PPT/PDF document "Lecture Notes Some notes on gradient des..." 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.

Lecture Notes Some notes on gradient descent Marc Toussaint Machine Learning Robotics lab FU Berlin Arnimallee Berlin Germany May Ill briey cover the following topics about gradient de scent Ste






Presentation on theme: "Lecture Notes Some notes on gradient descent Marc Toussaint Machine Learning Robotics lab FU Berlin Arnimallee Berlin Germany May Ill briey cover the following topics about gradient de scent Ste"— Presentation transcript: