ConceptAI & ML
ReLU
A non-linear activation function defined as the maximum of zero and the input value.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
3Each in their own terms, from the easiest level.
Phillip Isola
An activation function that maps all input data to the positive orthant by setting negative values to zero.Gilbert Strang
An activation function defined as the maximum of 0 and x, which is non-linear.
Lectures that assume it
2Connections
12The lectures that define it or assume it, and the concepts next to it.
Concepts7
- Activation function
- Linear function
- Exponential linear unit
- Guided backpropagation
- Leaky ReLU
- Maxout neuron