deepNN: dropoutProbs – R documentation

Become an expert in R — Interactive courses, Cheat Sheets, certificates and more!

dropoutProbs

dropoutProbs function

Description

A function to specify dropout for a neural network.

Usage

dropoutProbs(input = 1, hidden = 1)

Arguments

`input`	inclusion rate for input parameters
`hidden`	inclusion rate for hidden parameters

Value

returns these probabilities in an appropriate format for interaction with the network and train functions, see ?network and ?train

References

Ian Goodfellow, Yoshua Bengio, Aaron Courville, Francis Bach. Deep Learning. (2016)
Terrence J. Sejnowski. The Deep Learning Revolution (The MIT Press). (2018)
Neural Networks YouTube playlist by 3brown1blue: https://www.youtube.com/playlist?list=PLZHQObOWTQDNU6R1_67000Dx_ZCJB-3pi
http://neuralnetworksanddeeplearning.com/

Examples

netwts <- train( dat=d,
                 truth=truth,
                 net=net,
                 eps=0.01,
                 tol=0.95,           # run for 100 iterations
                 batchsize=10,       # note this is not enough
                 loss=multinomial(), # for convergence
                 dropout=dropoutProbs(input=0.8,hidden=0.5))

deepNN

Deep Learning

v1.0

GPL-3

Authors

Benjamin Taylor [aut, cre]

Initial release