Learner: Learner

Description Usage Arguments

Description

Abstraction for learning a subset of parameters of a learnable function using first order gradient values. For example momentum, AdaGrad, RMSProp, etc. are different types of learners with their own algorithms for learning parameter values using first order gradients. To instantiate a concrete learner, use the factory methods in this module.

Usage

1
Learner(parameters, learning_rate_schedule)

Arguments

parameters

– list of network parameters list of parameter associated with this learner

learning_rate_schedule

get_learning_rate(learner)


Microsoft/CNTK-R documentation built on May 28, 2019, 1:52 p.m.