August 2018
Intermediate to advanced
438 pages
12h 3m
English
Content preview from Hands-On Transfer Learning with Python
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
Start your free trial
RMSprop
RMSprop modifies the AdaGrad algorithm by taking the EWMA of previous squared gradients. It has the moving average parameter, ρ, which controls the length and scale of the moving average. This is one of the most successful algorithms for deep neural network training.