NeuralSens

Sensitivity Analysis of Neural Networks

Analysis functions to quantify inputs importance in neural network models. Functions are available for calculating and plotting the inputs importance and obtaining the activation function of each neuron layer and its derivatives. The importance of a given input is defined as the distribution of the derivatives of the output with respect to that input in each training data point.

Total

0

Last month

0

Last week

0

Average per day

0

Daily downloads

Total downloads

Description file content

Package
NeuralSens
Version
0.0.5
Title
Sensitivity Analysis of Neural Networks
Date
2019-07-11
Description
Analysis functions to quantify inputs importance in neural network models. Functions are available for calculating and plotting the inputs importance and obtaining the activation function of each neuron layer and its derivatives. The importance of a given input is defined as the distribution of the derivatives of the output with respect to that input in each training data point.
Author
José Portela González [aut], Antonio Muñoz San Roque [aut], Jaime Pizarroso Gonzalo [ctb, cre]
Maintainer
Jaime Pizarroso Gonzalo
Imports
ggplot2, gridExtra, NeuralNetTools, reshape2, caret, fastDummies, stringr
Suggests
h2o, neural, RSNNS, nnet, neuralnet
RoxygenNote
6.1.1
NeedsCompilation
no
URL
BugReports
https://github.com/JaiPizGon/NeuralSens/issues
License
GPL (>= 2)
Encoding
UTF-8
LazyData
true
Packaged
2019-07-11 15:11:49 UTC; jaime
Repository
CRAN
Date/Publication
2019-07-11 15:32:41 UTC

install.packages('NeuralSens')

0.0.5

a month ago

https://github.com/JaiPizGon/NeuralSens

Jaime Pizarroso Gonzalo

GPL (>= 2)

Imports

ggplot2, gridExtra, NeuralNetTools, reshape2, caret, fastDummies, stringr

Suggests

h2o, neural, RSNNS, nnet, neuralnet

Discussions