Papers by Shilpak Banerjee
EIS - Efficient and Trainable Activation Functions for Better Accuracy and Performance
Lecture Notes in Computer Science
Ergodic Theory and Dynamical Systems
In this article we demonstrate a way to extend the AbC (approximation by conjugation) method inve... more In this article we demonstrate a way to extend the AbC (approximation by conjugation) method invented by Anosov and Katok from the smooth category to the category of real-analytic diffeomorphisms on the torus. We present a general framework for such constructions and prove several results. In particular, we construct minimal but not uniquely ergodic diffeomorphisms and non-standard real-analytic realizations of toral translations.
Revisiting the Use of Squared Magnitude Function for the Optimal Approximation of (1+α)-Order Butterworth Filter
AEU - International Journal of Electronics and Communications
Ergodic Theory and Dynamical Systems, 2015
We extend some aspects of the smooth approximation by conjugation method to the real-analytic set... more We extend some aspects of the smooth approximation by conjugation method to the real-analytic set-up, and create examples of zero entropy, uniquely ergodic, real-analytic diffeomorphisms of the two-dimensional torus that are metrically isomorphic to some (Liouvillian) irrational rotations of the circle.
IEEE Access
Deep learning, at its core, contains functions that are the composition of a linear transformatio... more Deep learning, at its core, contains functions that are the composition of a linear transformation with a nonlinear function known as the activation function. In the past few years, there is an increasing interest in the construction of novel activation functions resulting in better learning. In this work, we propose three novel activation functions with learnable parameters, namely TanhSoft-1, TanhSoft-2, and TanhSoft-3, which are shown to outperform several well-known activation functions. For instance, replacing ReLU with TanhSoft-1, TanhSoft-2, and Tanhsot-3 improves top-1 classification accuracy by 6.06%, 5.75%, and 5.38% respectively on VGG-16(with batch-normalization), by 3.02%, 3.25% and 2.93% respectively on PreActResNet-34 in CIFAR-100 dataset, by 1.76%, 1.93%, and 1.82% respectively on WideResNet 28-10 in Tiny ImageNet dataset. TanhSoft-1, TanhSoft-2, and Tanhsot-3 outperformed ReLU on mean average precision (mAP) by 0.7%, 0.8%, and 0.6% respectively in object detection problem on SSD 300 model in Pascal VOC dataset. INDEX TERMS Deep learning, neural network, activation function.
Uploads
Papers by Shilpak Banerjee