Activation functions between network layers

Activation functions between network layers

activation(values = values_activation)

activation_2(values = values_activation)

values_activation

Format

An object of class character of length 23.

Arguments

values

A character string of possible values. See values_activation in examples below.

Details

This parameter is used in parsnip models for neural networks such as parsnip:::mlp().

Examples

values_activation
#>  [1] "celu"        "elu"         "exponential" "gelu"        "hardshrink" 
#>  [6] "hardsigmoid" "hardtanh"    "leaky_relu"  "linear"      "log_sigmoid"
#> [11] "relu"        "relu6"       "rrelu"       "selu"        "sigmoid"    
#> [16] "silu"        "softmax"     "softplus"    "softshrink"  "softsign"   
#> [21] "swish"       "tanh"        "tanhshrink" 
activation()
#> Activation Function (qualitative)
#> 23 possible values include:
#> 'celu', 'elu', 'exponential', 'gelu', 'hardshrink', 'hardsigmoid', 'hardtanh',
#> 'leaky_relu', 'linear', 'log_sigmoid', 'relu', 'relu6', 'rrelu', 'selu',
#> 'sigmoid', 'silu', 'softmax', 'softplus', …, 'tanh', and 'tanhshrink'