5,337
edits
Deep Learning: Difference between revisions
→Basics
(→Basics) |
|||
| Line 43: | Line 43: | ||
* RMSProp | * RMSProp | ||
* Adam | * Adam | ||
==DL Optimization== | |||
The role of "over-parameterization". | |||
In general, you can have poor local minimums and saddle points (with pos+neg Hessian). | |||
However, in practice GD & SGD work pretty well. | |||
Lecture 2 (Sept 3) is about Liu ''et al.'' <ref name="liu2020towards></ref> | |||
==Misc== | ==Misc== | ||