Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks

25 July 2017

Papers citing "Dual Rectified Linear Units (DReLUs): A Replacement for Tanh Activation Functions in Quasi-Recurrent Neural Networks"

3 / 3 papers shown

Title
How important are activation functions in regression and classification? A survey, performance comparison, and future directions Ameya Dilip Jagtap George Karniadakis AI4CE 37 71 0 06 Sep 2022
Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark S. Dubey S. Singh B. B. Chaudhuri 41 643 0 29 Sep 2021
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation Yonghui Wu M. Schuster Z. Chen Quoc V. Le Mohammad Norouzi ... Alex Rudnick Oriol Vinyals G. Corrado Macduff Hughes J. Dean AIMat 716 6,746 0 26 Sep 2016