4 citations · 6 across the 5 of their papers we have counts for
7 papers
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…
Slow entropy for some Anosov-Katok diffeomorphisms
Shilpak Banerjee, Philipp Kunde, Daren Wei
The Anosov-Katok method is one of the most powerful tools of constructing smooth volume-preserving diffeomorphisms of entropy zero with prescribed ergodic or topological properties…
Orthogonal-Padé Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks
Koushik Biswas, Shilpak Banerjee, Ashish Kumar Pandey
We have proposed orthogonal-Padé activation functions, which are trainable activation functions and show that they have faster learning capability and improves the accuracy in stan…
EIS -- a family of activation functions combining Exponential, ISRU, and Softplus
Koushik Biswas, Sandeep Kumar, Shilpak Banerjee +1
Activation functions play a pivotal role in the function learning using neural networks. The non-linearity in the learned function is achieved by repeated use of the activation fun…
Slow entropy of some combinatorial constructions
Shilpak Banerjee, Philipp Kunde, Daren Wei
Measure-theoretic slow entropy is a more refined invariant than the classical measure-theoretic entropy to characterize the complexity of dynamical systems with subexponential grow…
TanhSoft -- a family of activation functions combining Tanh and Softplus
Koushik Biswas, Sandeep Kumar, Shilpak Banerjee +1
Deep learning at its core, contains functions that are composition of a linear transformation with a non-linear function known as activation function. In past few years, there is a…