Continuously Differentiable Exponential Linear Unit.

The CeLU activation function is defined as:

celu(x) = alpha * (exp(x / alpha) - 1) for x < 0,celu(x) = x for x >= 0.

where alpha is a scaling parameter that controls the activation's shape.

Usage

activation_celu(x, alpha = 1)

Arguments

x

Input tensor.

alpha

The value for the CeLU formulation. Defaults to 1.0.

Value

A tensor, the result from applying the activation to the input tensor x.

Reference

• Barron, J. T., 2017

See also

Other activations:
activation_elu()
activation_exponential()
activation_gelu()
activation_glu()
activation_hard_shrink()
activation_hard_sigmoid()
activation_hard_tanh()
activation_leaky_relu()
activation_linear()
activation_log_sigmoid()
activation_log_softmax()
activation_mish()
activation_relu()
activation_relu6()
activation_selu()
activation_sigmoid()
activation_silu()
activation_soft_shrink()
activation_softmax()
activation_softplus()
activation_softsign()
activation_sparse_plus()
activation_sparsemax()
activation_squareplus()
activation_tanh()
activation_tanh_shrink()
activation_threshold()