brainpy.math.surrogate.LeakyRelu#

class brainpy.math.surrogate.LeakyRelu(alpha=0.1, beta=1.0, forward_use_surrogate=False)[source]#

Judge spiking state with the Leaky ReLU function.

See also

leaky_relu

__init__(alpha=0.1, beta=1.0, forward_use_surrogate=False)[source]#

Methods

__init__([alpha, beta, forward_use_surrogate])

call(x)

Call the function for surrogate gradient propagation.

surrogate_fun(x)

The surrogate function.

surrogate_grad(dz, x)

The gradient for the surrogate function.

true_fun(x)

The original true function.