11.1. Argmax

11.1.1. Argmax API

class fhez.nn.activation.argmax.Argmax

Argmax activation, compute sparse array of highest activation.

backward(gradient: numpy.ndarray)

Calculate the argmax derivative with respect to each input.

Argmax.

property cost

Get computational cost of this activation.

forward(x: numpy.ndarray)

Calculate the argmax of some input \(x\) along its first axis.

Argmax.

update()

Update parameters, so nothing for argmax.

updates()

Update parameters using average of gradients so none for argmax.