rmsprop

In Hinton’s lecture, it is described as dividing the learning rate for a given weight by a running average of the magnitude of recent gradients for that weights.

Q1 – What is the intuition behind this method?

Q2 – What problems does it help to solve?

Advertisements

0 Responses to “rmsprop”



  1. Leave a Comment

Leave a Reply

Please log in using one of these methods to post your comment:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s





%d bloggers like this: