e3x.nn.activations.silu

e3x.nn.activations.silu(x)[source]

SiLU/Swish activation function.

Computes the gated linear activation with:

\[\mathrm{gate}(x) = \mathrm{sigmoid}(x)\]

For scalar inputs, this is equivalent to:

\[\mathrm{silu}(x) = x \cdot \mathrm{sigmoid}(x) = \frac{x}{1 + e^{-x}}\]

../_images/e3x.nn.activations.silu_0_0.svg

Parameters:: x (Union[Float[Array, '... 1 (max_degree+1)**2 num_features'], Float[Array, '... 2 (max_degree+1)**2 num_features']]) – Input features to which the nonlinearity is applied.
Return type:: Union[Float[Array, '... 1 (max_degree+1)**2 num_features'], Float[Array, '... 2 (max_degree+1)**2 num_features']]
Returns:: The result of applying the nonlinearity to the input features.