most citedOrthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

2 papers · 1 filter

cs.LG2021

SAU: Smooth activation function using convolution with approximate identities

Koushik Biswas, Sandeep Kumar, Shilpak Banerjee +1

Well-known activation functions like ReLU or Leaky ReLU are non-differentiable at the origin. Over the years, many smooth approximations of ReLU have been proposed using various sm…

cs.LG2021

Intensity Prediction of Tropical Cyclones using Long Short-Term Memory Network

Koushik Biswas, Sandeep Kumar, Ashish Kumar Pandey

Tropical cyclones can be of varied intensity and cause a huge loss of lives and property if the intensity is high enough. Therefore, the prediction of the intensity of tropical cyc…