Fig.1

Concept

RMSProp

RMSProp (Root Mean Square Propagation) is a stochastic gradient descent variant that gives each parameter its own effective learning rate, scaled by a running estimate of that parameter's recent gradient magnitude. It was proposed by Geoffrey Hinton in a Coursera lecture,…

The rest of “RMSProp” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library