FAU Lecture Notes in Pattern Recognition
How Norms drive the Direction of your Optimization…
Norm-dependent Gradients
These are the lecture notes for FAU’s YouTube Lecture “Pattern Recognition”. This is a full transcript of the lecture video & matching slides. The sources for the slides are available here. We hope, you enjoy this as much as the videos. This transcript was almost entirely machine generated using AutoBlog and only minor manual modifications were performed. If you spot mistakes, please let us know!
Navigation
Previous Chapter / Watch this Video / Next Chapter / Top Level
Welcome back to pattern recognition. Today we want to look a bit more into optimization and the topic today will be looking into the actual update direction. We’ve seen the gradient descent methods in the previous video and today we want to have a couple of thoughts on how to pick the particular update direction.
These are different kinds of steepest descent methods and even the normalized ones we might want to consider what update direction we actually want to choose. What we actually…