Package: NeuralSens 1.1.3

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 <doi:10.18637/jss.v102.i07>.

Authors:José Portela González [aut], Antonio Muñoz San Roque [aut], Jaime Pizarroso Gonzalo [aut, ctb, cre]

NeuralSens_1.1.3.tar.gz
NeuralSens_1.1.3.zip(r-4.5)NeuralSens_1.1.3.zip(r-4.4)NeuralSens_1.1.3.zip(r-4.3)
NeuralSens_1.1.3.tgz(r-4.4-any)NeuralSens_1.1.3.tgz(r-4.3-any)
NeuralSens_1.1.3.tar.gz(r-4.5-noble)NeuralSens_1.1.3.tar.gz(r-4.4-noble)
NeuralSens_1.1.3.tgz(r-4.4-emscripten)NeuralSens_1.1.3.tgz(r-4.3-emscripten)
NeuralSens.pdf |NeuralSens.html✨
NeuralSens/json (API)

# Install 'NeuralSens' in R:
install.packages('NeuralSens', repos = c('https://jaipizgon.r-universe.dev', 'https://cloud.r-project.org'))

Peer review:

Bug tracker:https://github.com/jaipizgon/neuralsens/issues

Datasets:

On CRAN:

5.42 score 14 stars 14 scripts 408 downloads 29 exports 122 dependencies

Last updated 1 months agofrom:63fbf3b5fc. Checks:OK: 1 WARNING: 6. Indexed: yes.

TargetResultDate
Doc / VignettesOKOct 26 2024
R-4.5-winWARNINGOct 26 2024
R-4.5-linuxWARNINGOct 26 2024
R-4.4-winWARNINGOct 26 2024
R-4.4-macWARNINGOct 26 2024
R-4.3-winWARNINGOct 26 2024
R-4.3-macWARNINGOct 26 2024

Exports:ActFuncAlphaSensAnalysisAlphaSensCurveChangeBootAlphaCombineSensDer2ActFuncDer3ActFuncDerActFuncdiag3Darraydiag3Darray<-diag4Darraydiag4Darray<-find_critical_valueHessDotPlotHessFeaturePlotHessianMLPHessMLPHessToSensMLPis.HessMLPis.SensMLPkStepMAlgorithmPlotSensMLPSensAnalysisMLPSensDotPlotSensFeaturePlotSensitivityPlotsSensMatPlotSensMLPSensTimePlot

Dependencies:aplotbackportsbase64encbslibcachemcaretcheckmateclasscliclockclustercodetoolscolorspacecpp11data.tablediagramdigestdplyre1071evaluatefansifarverfastDummiesfastmapfontawesomeforeachforeignFormulafsfuturefuture.applygenericsggbreakggforceggfunggnewscaleggplot2ggplotifyggrepelglobalsgluegowergridExtragridGraphicsgtablehardhathighrHmischtmlTablehtmltoolshtmlwidgetsipredisobanditeratorsjquerylibjsonliteKernSmoothknitrlabelinglatticelavalifecyclelistenvlubridatemagrittrMASSMatrixmemoisemgcvmimeModelMetricsmunsellNeuralNetToolsnlmennetnumDerivparallellypatchworkpillarpkgconfigplyrpolyclippROCprodlimprogressrproxypurrrR6rappdirsRColorBrewerRcppRcppEigenrecipesreshape2rlangrmarkdownrpartrstudioapisassscalesshapeSQUAREMstringistringrsurvivalsystemfontstibbletidyrtidyselecttimechangetimeDatetinytextweenrtzdbutf8vctrsviridisviridisLitewithrxfunyamlyulab.utils

Readme and manuals

Help Manual

Help pageTopics
Activation function of neuronActFunc
Sensitivity alpha-curve associated to MLP functionAlphaSensAnalysis
Sensitivity alpha-curve associated to MLP function of an input variableAlphaSensCurve
Change significance of boot SensMLP ClassChangeBootAlpha
Sensitivity analysis plot over time of the dataCombineSens
Plot sensitivities of a neural network modelComputeHessMeasures
Plot sensitivities of a neural network modelComputeSensMeasures
Data frame with 4 variablesDAILY_DEMAND_TR
Data frame with 3 variablesDAILY_DEMAND_TV
Second derivative of activation function of neuronDer2ActFunc
Third derivative of activation function of neuronDer3ActFunc
Derivative of activation function of neuronDerActFunc
Define function to create a 'diagonal' array or get the diagonal of an arraydiag3Darray
Define function to change the diagonal of arraydiag3Darray<-
Define function to create a 'diagonal' array or get the diagonal of an arraydiag4Darray
Define function to change the diagonal of arraydiag4Darray<-
Find Critical Valuefind_critical_value
Second derivatives 3D scatter or surface plot against input valuesHessDotPlot
Feature sensitivity plotHessFeaturePlot
Sensitivity of MLP modelsHessianMLP HessianMLP.default HessianMLP.H2OMultinomialModel HessianMLP.H2ORegressionModel HessianMLP.list HessianMLP.mlp HessianMLP.nn HessianMLP.nnet HessianMLP.nnetar HessianMLP.numeric HessianMLP.train
Constructor of the HessMLP ClassHessMLP
Convert a HessMLP to a SensMLP objectHessToSensMLP
Check if object is of class 'HessMLP'is.HessMLP
Check if object is of class 'SensMLP'is.SensMLP
k-StepM Algorithm for Hypothesis TestingkStepMAlgorithm
NeuralSens: Sensitivity Analysis of Neural NetworksNeuralSens-package NeuralSens
Plot method for the HessMLP Classplot.HessMLP
Plot method for the SensMLP Classplot.SensMLP
Neural network structure sensitivity plotPlotSensMLP
Print method for the HessMLP Classprint.HessMLP
Print method for the SensMLP Classprint.SensMLP
Print method of the summary HessMLP Classprint.summary.HessMLP
Print method of the summary SensMLP Classprint.summary.SensMLP
Sensitivity of MLP modelsSensAnalysisMLP SensAnalysisMLP.default SensAnalysisMLP.H2OMultinomialModel SensAnalysisMLP.H2ORegressionModel SensAnalysisMLP.list SensAnalysisMLP.mlp SensAnalysisMLP.nn SensAnalysisMLP.nnet SensAnalysisMLP.nnetar SensAnalysisMLP.numeric SensAnalysisMLP.train
Sensitivity scatter plot against input valuesSensDotPlot
Feature sensitivity plotSensFeaturePlot
Plot sensitivities of a neural network modelSensitivityPlots
Plot sensitivities of a neural network modelSensMatPlot
Constructor of the SensMLP ClassSensMLP
Sensitivity analysis plot over time of the dataSensTimePlot
Simulated data to test the package functionalitiessimdata
Summary Method for the HessMLP Classsummary.HessMLP
Summary Method for the SensMLP Classsummary.SensMLP