Calculates the importance of each input model based on information criterion and returns which node is least important
Usage
input_importance(
X,
y,
q,
n_init,
inf_crit = "BIC",
task = "regression",
unif = 3,
addition = FALSE,
X_full = NULL,
maxit = 1000,
...
)Arguments
- X
Matrix of covariates
- y
Vector of response
- q
Number of hidden nodes
- n_init
Number of random initialisations (tracks)
- inf_crit
Information criterion:
"BIC"(default),"AIC"or"AICc"- task
"regression"(default) or"classification"- unif
Random initial values max value
- addition
Switch for addition step (default FALSE)
- X_full
Full matrix of covariates if X has some dropped
- maxit
maximum number of iterations for nnet (default = 100)
- ...
additional argument for nnet