deepNN: no_regularisation – R documentation

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

no_regularisation

no_regularisation function

Description

A function to return the no regularisation strategy for a network object.

Usage

no_regularisation()

Value

list containing functions to evaluate the cost modifier and grandient modifier

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

# Example in context: NOTE with the network function
# no_regularisation() is the default, so this argument
# actually need not be included

net <- network( dims = c(784,16,16,10),
                regulariser = no_regularisation(),
                activ=list(ReLU(),logistic(),softmax()))

deepNN

Deep Learning

v1.0

GPL-3

Authors

Benjamin Taylor [aut, cre]

Initial release