Optimizer Activation Function

Introduced by ZHANG et al. in 0/1 Deep Neural Networks via Block Coordinate Descent

A new activation function named NIPUNA : f(x)=max⁡〖(g(x),x)〗 where g(x)=x/(〖(1+e〗^(-βx)))

Source: 0/1 Deep Neural Networks via Block Coordinate Descent

Read Paper

Paper	Code	Results	Date	Stars

Task	Papers	Share
Medical Diagnosis	1	100.00%

This feature is experimental; we are continuously improving our matching algorithm.

Component	Type	Add Remove
🤖 No Components Found	You can add them if they exist; e.g. Mask R-CNN uses RoIAlign