s_NLA: NonLinear Activation unit Regression (NLA) [R]
In egenn/rtemis: Machine Learning and Visualization

s_NLA

R Documentation

NonLinear Activation unit Regression (NLA) [R]

Description

Train an equivalent of a 1 hidden unit neural network with a defined nonlinear activation function using optim

Usage

s_NLA(
  x,
  y = NULL,
  x.test = NULL,
  y.test = NULL,
  activation = softplus,
  b_o = mean(y),
  W_o = 1,
  b_h = 0,
  W_h = 0.01,
  optim.method = "BFGS",
  control = list(),
  x.name = NULL,
  y.name = NULL,
  print.plot = FALSE,
  plot.fitted = NULL,
  plot.predicted = NULL,
  plot.theme = rtTheme,
  question = NULL,
  verbose = TRUE,
  trace = 0,
  outdir = NULL,
  save.mod = ifelse(!is.null(outdir), TRUE, FALSE),
  ...
)

Arguments

`x`	Numeric vector or matrix / data frame of features i.e. independent variables
`y`	Numeric vector of outcome, i.e. dependent variable
`x.test`	Numeric vector or matrix / data frame of testing set features Columns must correspond to columns in `x`
`y.test`	Numeric vector of testing set outcome
`activation`	Function: Activation function to use. Default = softplus
`b_o`	Float, vector (length y): Output bias. Defaults to `mean(y)`
`W_o`	Float: Output weight. Defaults to 1
`b_h`	Float: Hidden layer bias. Defaults to 0
`W_h`	Float, vector (length `NCOL(x)`): Hidden layer weights. Defaults to 0
`optim.method`	Character: Optimization method to use: "Nelder-Mead", "BFGS", "CG", "L-BFGS-B", "SANN", "Brent". See `stats::optim` for more details. Default = `"BFGS"`
`control`	List: Control parameters passed to `stats::optim`
`x.name`	Character: Name for feature set
`y.name`	Character: Name for outcome
`print.plot`	Logical: if TRUE, produce plot using `mplot3` Takes precedence over `plot.fitted` and `plot.predicted`.
`plot.fitted`	Logical: if TRUE, plot True (y) vs Fitted
`plot.predicted`	Logical: if TRUE, plot True (y.test) vs Predicted. Requires `x.test` and `y.test`
`plot.theme`	Character: "zero", "dark", "box", "darkbox"
`question`	Character: the question you are attempting to answer with this model, in plain language.
`verbose`	Logical: If TRUE, print summary to screen.
`trace`	Integer: If > 0, print model summary.
`outdir`	Path to output directory. If defined, will save Predicted vs. True plot, if available, as well as full model output, if `save.mod` is TRUE
`save.mod`	Logical: If TRUE, save all output to an RDS file in `outdir` `save.mod` is TRUE by default if an `outdir` is defined. If set to TRUE, and no `outdir` is defined, outdir defaults to `paste0("./s.", mod.name)`
`...`	Additional arguments to be passed to `sigreg`

Details

Since we are using optim, results will be sensitive to the combination of optimizer method (See optim::method for details), initialization values, and activation function.

Value

Object of class rtemis

Author(s)

E.D. Gennatas

Other Supervised Learning: s_AdaBoost(), s_AddTree(), s_BART(), s_BRUTO(), s_BayesGLM(), s_C50(), s_CART(), s_CTree(), s_EVTree(), s_GAM(), s_GAM.default(), s_GAM.formula(), s_GBM(), s_GLM(), s_GLMNET(), s_GLMTree(), s_GLS(), s_H2ODL(), s_H2OGBM(), s_H2ORF(), s_HAL(), s_KNN(), s_LDA(), s_LM(), s_LMTree(), s_LightCART(), s_LightGBM(), s_MARS(), s_MLRF(), s_NBayes(), s_NLS(), s_NW(), s_PPR(), s_PolyMARS(), s_QDA(), s_QRNN(), s_RF(), s_RFSRC(), s_Ranger(), s_SDA(), s_SGD(), s_SPLS(), s_SVM(), s_TFN(), s_XGBoost(), s_XRF()