quantax.nn.SinhShift#

class quantax.nn.SinhShift#

Bases: Theta0Layer

\(f(x) = (\sinh(x) + 1) \exp(\theta_0)\)

Note

No matter which input data type is provided, the output data type is always given by quantax.get_default_dtype.

rescale(maximum: Array) → Theta0Layer#

Rescale the function output by adjusting \(\theta_0\).

Parameters:: maximum – The maximum output m obtained from this activation function. \(\theta_0\) is adjusted as \(\theta'_0 = \theta_0 - \log(m)\) so that the maximum output is rescaled to 1.
Returns:: The layer with adjusted \(\theta_0\).

Note

This method generates a new layer while doesn’t modify the existing layer.

Attributes

theta0