APTx: better activation function than MISH, SWISH, and ReLU's variants used in deep learning

10 September 2022

Papers citing "APTx: better activation function than MISH, SWISH, and ReLU's variants used in deep learning"

6 / 6 papers shown

Title
Improving Classification Neural Networks by using Absolute activation function (MNIST/LeNET-5 example) Oleg I.Berngardt 66 2 0 23 Apr 2023
Review and Comparison of Commonly Used Activation Functions for Deep Neural Networks Tomasz Szandała 98 287 0 15 Oct 2020
Deep Learning using Rectified Linear Units (ReLU) Abien Fred Agarap 56 3,212 0 22 Mar 2018
Searching for Activation Functions Prajit Ramachandran Barret Zoph Quoc V. Le 62 606 0 16 Oct 2017
Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) Djork-Arné Clevert Thomas Unterthiner Sepp Hochreiter 271 5,518 0 23 Nov 2015
Deeply learned face representations are sparse, selective, and robust Yi Sun Xiaogang Wang Xiaoou Tang CVBM 310 922 0 03 Dec 2014