neuralsens

The neuralsens package facilitates sensitivity analysis on neural network models, quantifying input importance. It provides functions for calculating and plotting input significance, and obtaining neuron layer activation functions and derivatives. Compatible with models created in R and Python, it's a robust toolkit for understanding input contributions in neural networks.


License
Other
Install
pip install neuralsens==0.0.3.dev53

Documentation

NeuralSens

Jaime Pizarroso Gonzalo, jpizarroso@comillas.edu

Antonio Muñoz San Roque, Antonio.Munoz@iit.comillas.edu

José Portela González, jose.portela@iit.comillas.edu

  • R : CRAN status CRAN_Download_Badge
  • Python : pypi Downloads python os

This is the development repository for the neuralsens Python Badge package and the NeuralSens R Badge package. Functions within this package can be used for the analysis of neural network models created in R.

How to install

For Python, the last version of the neuralsens package can be installed using pip or conda:

$ pip install neuralsens
$ conda install -c jaipizgon neuralsens

For R, the last version of the NeuralSens package can be installed from Github or CRAN:

# Github 
install.packages('devtools')
library(devtools)
install_github('JaiPizGon/NeuralSens/R')
# CRAN
install.packages('NeuralSens')

Citation

Please, to cite NeuralSens in publications use:

Pizarroso J, Portela J, Muñoz A (2022). “NeuralSens: Sensitivity Analysis of Neural Networks.” Journal of Statistical Software, 102(7), 1-36. doi: 10.18637/jss.v102.i07 (URL: https://doi.org/10.18637/jss.v102.i07).

License

This package is released in the public domain under the General Public License GPL.

Association

Package created in the Institute for Research in Technology (IIT), link to homepage