Activation Functions

Shifted Softplus is an activation function ${\rm ssp}(x) = \ln( 0.5 e^{x} + 0.5 )$, which SchNet employs as non-linearity throughout the network in order to obtain a smooth potential energy surface. The shifting ensures that ${\rm ssp}(0) = 0$ and improves the convergence of the network. This activation function shows similarity to ELUs, while having infinite order of continuity.

Source: SchNet: A continuous-filter convolutional neural network for modeling quantum interactions


Paper Code Results Date Stars


Task Papers Share
Formation Energy 3 42.86%
BIG-bench Machine Learning 2 28.57%
Drug Discovery 1 14.29%
Total Energy 1 14.29%


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