What is ReLU?

Three deep ReLU networks learn sin(10x) + 0.5sin(3x)

The Hidden Problem with ReLU (And How Leaky ReLU Fixes It)

Three ReLU networks with different widths learning noisy sin

Three ReLU networks with different widths learning noisy step(x)

ReLU Isn’t Always the Best Choice

Three ReLU networks with different widths learning noisy parabola

Swish vs ReLU — Why Swish Works So Well

ReLU vs Leaky ReLU vs ELU Explained Simply

What is an Activation Function?

ReLU Fixed One Problem… Created Another 😬

three ReLU networks learn sin(x) + x

ReLU vs Leaky ReLU Explained

ReLU vs Sigmoid vs Tanh: Which Activation Function Wins?

How ReLU neural network learns functions?

ReLU Explained in 60 Seconds