relu

class saiunit.math.relu(x)

Rectified linear unit activation function.

Computes the element-wise function:

\[\mathrm{relu}(x) = \max(x, 0)\]

except under differentiation, we take:

\[\nabla \mathrm{relu}(0) = 0\]

For more information see Numerical influence of ReLU’(0) on backpropagation.

Parameters:

x (Quantity | Array | ndarray | bool | number | bool | int | float | complex) – Input array. If a Quantity with physical units is provided, the units are preserved in the output.

Returns:

out – An array with the same shape as x where negative values are replaced by zero. Units are preserved when present.

Return type:

Quantity | Array

Examples

>>> import jax.numpy as jnp
>>> import saiunit.math as sumath
>>> sumath.relu(jnp.array([-2., -1., 0., 1., 2.]))
Array([0., 0., 0., 1., 2.], dtype=float32)

>>> import saiunit as u
>>> q = u.Quantity(jnp.array([-1., 0., 1.]), unit=u.meter)
>>> sumath.relu(q)  # units are preserved