Softsign Activation

GeneralIntroduced 200012 papers

Description

Softsign is an activation function for neural networks:

$f\left(x\right) = \left(\frac{x}{|x|+1}\right)$

Image Source: Sefik Ilkin Serengil

Papers Using This Method

Trainable Activations for Image Classification2023-01-26 Clarinet: A Music Retrieval System2022-10-23 Estimating Parameters of the Tree Root in Heterogeneous Soil Environments via Mask-Guided Multi-Polarimetric Integration Neural Network2021-12-27 ParaNet: Deep Regular Representation for 3D Point Clouds2020-12-05 Learning from a Complementary-label Source Domain: Theory and Algorithms2020-08-04 Clarinet: A One-step Approach Towards Budget-friendly Unsupervised Domain Adaptation2020-07-29 Parallel Neural Text-to-Speech2020-01-01 Multi-Speaker End-to-End Speech Synthesis2019-07-09 Non-Autoregressive Neural Text-to-Speech2019-05-21 Neural source-filter waveform models for statistical parametric speech synthesis2019-04-27 ClariNet: Parallel Wave Generation in End-to-End Text-to-Speech2018-07-19 Deep Voice 3: Scaling Text-to-Speech with Convolutional Sequence Learning2017-10-20