AI engineering glossary · Deep learning core
What is Parametric ReLU?
Parametric ReLU (also called PReLU): A version of Leaky ReLU in which the slope applied to negative inputs is itself a learnable parameter, trained along with the weights. It lets each layer or channel decide how much negative signal to keep.
Parametric ReLU: an example
If training learns a slope of 0.25 for a layer, an input of -4 becomes -1.
Related terms
More Deep learning core terms
Where you learn it
Parametric ReLU is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.