class brainpy.dnn.RReLU(lower=0.125, upper=0.3333333333333333, inplace=False)[source]#

Applies the randomized leaky rectified liner unit function, element-wise, as described in the paper:

Empirical Evaluation of Rectified Activations in Convolutional Network.

The function is defined as:

\[\begin{split}\text{RReLU}(x) = \begin{cases} x & \text{if } x \geq 0 \\ ax & \text{ otherwise } \end{cases}\end{split}\]

where \(a\) is randomly sampled from uniform distribution \(\mathcal{U}(\text{lower}, \text{upper})\).

  • lower (float) – lower bound of the uniform distribution. Default: \(\frac{1}{8}\)

  • upper (float) – upper bound of the uniform distribution. Default: \(\frac{1}{3}\)

  • inplace (bool) – can optionally do the operation in-place. Default: False

  • Input: \((*)\), where \(*\) means any number of dimensions.

  • Output: \((*)\), same shape as the input.


>>> import brainpy as bp
>>> import brainpy.math as bm
>>> m = bp.dnn.RReLU(0.1, 0.3)
>>> input = bm.random.randn(2)
>>> output = m(input)

The function to specify the updating rule.

Return type:

TypeVar(ArrayType, Array, Variable, TrainVar, Array, ndarray)