Formula interface for elm_train, transforms a data frame and formula
into the necessary input for elm_train, automatically calls onehot_encode
for classification.
elm(
formula,
data,
nhid,
actfun,
init_weights = "normal_gaussian",
bias = FALSE,
moorep_pseudoinv_tol = 0.01,
leaky_relu_alpha = 0,
seed = 1,
verbose = FALSE
)formula used to specify the regression or classification.
data.frame with the data
a numeric value specifying the hidden neurons. Must be >= 1
a character string specifying the type of activation function. It should be one of the following : 'sig' ( sigmoid ), 'sin' ( sine ), 'radbas' ( radial basis ), 'hardlim' ( hard-limit ), 'hardlims' ( symmetric hard-limit ), 'satlins' ( satlins ), 'tansig' ( tan-sigmoid ), 'tribas' ( triangular basis ), 'relu' ( rectifier linear unit ) or 'purelin' ( linear )
a character string spcecifying the distribution from which the input-weights and the bias should be initialized. It should be one of the following : 'normal_gaussian' (normal / Gaussian distribution with zero mean and unit variance), 'uniform_positive' ( in the range [0,1] ) or 'uniform_negative' ( in the range [-1,1] )
either TRUE or FALSE. If TRUE then bias weights will be added to the hidden layer
a numeric value. See the references web-link for more details on Moore-Penrose pseudo-inverse and specifically on the pseudo inverse tolerance value
a numeric value between 0.0 and 1.0. If 0.0 then a simple relu ( f(x) = 0.0 for x < 0, f(x) = x for x >= 0 ) activation function will be used, otherwise a leaky-relu ( f(x) = alpha * x for x < 0, f(x) = x for x >= 0 ). It is applicable only if actfun equals to 'relu'
a numeric value specifying the random seed. Defaults to 1
a boolean. If TRUE then information will be printed in the console
elm object which can be used with predict, residuals and fitted.
elm(Species ~ ., data = iris, nhid = 20, actfun="sig")
#> Extreme learning model, elm (classification):
#>
#> call: elm(Species ~ ., data = iris, nhid = 20, actfun = "sig")
#> hidden units : 20
#> activation function: sig
#> accuracy : 0.9733333
#>
#> confusion matrix :
#> predicted
#> observed setosa versicolor virginica
#> setosa 50 0 0
#> versicolor 0 48 2
#> virginica 0 2 48
mod_elm <- elm(Species ~ ., data = iris, nhid = 20, actfun="sig")
# predict classes
predict(mod_elm, newdata = iris[1:3,-5])
#> [1] setosa setosa setosa
#> Levels: setosa versicolor virginica
# predict probabilities
predict(mod_elm, newdata = iris[1:3,-5], type="prob")
#> setosa versicolor virginica
#> [1,] 0.9775201 0.02021516 0.002264738
#> [2,] 0.9519374 0.02871766 0.019344988
#> [3,] 0.9620877 0.02854287 0.009369432
# predict elm output
predict(mod_elm, newdata = iris[1:3,-5], type="raw")
#> setosa versicolor virginica
#> [1,] 1.018682 -0.02106638 0.002360102
#> [2,] 1.009991 -0.03046901 0.020524740
#> [3,] 1.020310 -0.03027020 0.009936443
data("Boston")
elm(medv ~ ., data = Boston, nhid = 40, actfun="relu")
#> Extreme learning model, elm (regression):
#>
#> call: elm(medv ~ ., data = Boston, nhid = 40, actfun = "relu")
#> hidden units : 40
#> activation function: relu
#> mse : 20.20491
data("ionosphere")
elm(class ~ ., data = ionosphere, nhid=20, actfun="relu")
#> Extreme learning model, elm (classification):
#>
#> call: elm(class ~ ., data = ionosphere, nhid = 20, actfun = "relu")
#> hidden units : 20
#> activation function: relu
#> accuracy : 0.8603989
#>
#> confusion matrix :
#> predicted
#> observed b g
#> b 89 37
#> g 12 213