Activations functions can either be used through layer_activation(), or
through the activation argument supported by all forward layers.
activation_relu(x, alpha = 0, max_value = NULL, threshold = 0)activation_elu(x, alpha = 1)
activation_selu(x)
activation_hard_sigmoid(x)
activation_linear(x)
activation_sigmoid(x)
activation_softmax(x, axis = -1)
activation_softplus(x)
activation_softsign(x)
activation_tanh(x)
activation_exponential(x)
Tensor
Alpha value
Max value
Threshold value for thresholded activation.
Integer, axis along which the softmax normalization is applied
Tensor with the same shape and dtype as x.
activation_selu() to be used together with the initialization "lecun_normal".
activation_selu() to be used together with the dropout variant "AlphaDropout".
activation_selu(): Self-Normalizing Neural Networks