Gradient Methods for Machine Learning thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Gradient Methods for Machine Learning

Published on Feb 25, 20079964 Views

Gradient methods locally optimize an unknown differentiable function, and thus provide the engines that drive much machine learning. Here we'll take a look under the hood, beginning with brief overvie

Related categories

Chapter list

Course Overview00:01
Classical Gradient Methods01:34
Function Optimization04:01
Methods by Gradient Order06:46
Direct (Gradient-Free) Methods08:22
Prototypical Direct Method09:25
Direct Methods: Advantages13:23
Direct Methods: Disadvantages18:33
Gradient Descent21:42
Gradient Descent: Disadvantages25:08
Newton’s Method31:52
Newton’s Method34:37
Gauss-Newton Approximation38:32
Levenberg-Marquardt48:09
Quasi-Newton: BFGS50:42
Conjugate Gradient53:15
Conjugate Gradient: Properties57:36