Gated Linear Unit (GLU) activation function.

The GLU activation function is defined as:

glu(x) = a * sigmoid(b),

where x is split into two equal parts a and b along the given axis.

Usage

activation_glu(x, axis = -1L)

Arguments

x

Input tensor.

axis

The axis along which to split the input tensor. Defaults to -1.

Value

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

Reference

• Dauphin et al., 2017

See also

Other activations:
activation_celu()
activation_elu()
activation_exponential()
activation_gelu()
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()