Lecture 17 – Gradient Descent
Presented by Anthony D. Joseph
Content by Josh Hug, Joseph Gonzalez
- video playlist
- code HTML
- (optional) Loss Game
The Quick Check for this lecture is due Monday, November 2nd at 11:59PM. A random one of the following Google Forms will give you an alphanumeric code once you submit; you should take this code and enter it into the “Lecture 17” question in the “Quick Check Codes” assignment on Gradescope to get credit for submitting this Quick Check.
Gradient descent in one dimension. Convexity.
Various methods of optimizing loss functions in one dimension.
Gradient descent in multiple dimensions. Interpretation of gradients.
Stochastic gradient descent (SGD). Comparison between gradient descent and SGD.