gfdl.weights.zeros#

zeros(d, h, **kwargs)[source]#

The weight function setting all weights to zero.

This function is useful to test out the effect of the data features in isolation.

Parameters:
dint

Number of features in a sample or number of neurons in the previous hidden layer.

hint

Number of neurons in the current hidden layer.

Returns:
ndarray or scalar

All zeros.

Other Parameters:
**kwargsdict

Needed for keyword arguments and compatibility with other weight function apis but not relevant for this function.