Activation Functions

Tanh Activation

Tanh Activation is an activation function used for neural networks:

$$f\left(x\right) = \frac{e^{x} - e^{-x}}{e^{x} + e^{-x}}$$

Historically, the tanh function became preferred over the sigmoid function as it gave better performance for multi-layer neural networks. But it did not solve the vanishing gradient problem that sigmoids suffered, which was tackled more effectively with the introduction of ReLU activations.

Image Source: Junxi Feng

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Prediction 27 3.40%
Deep Learning 24 3.02%
Sentiment Analysis 21 2.64%
Time Series Forecasting 19 2.39%
Translation 16 2.02%
Management 15 1.89%
Computational Efficiency 15 1.89%
Decoder 13 1.64%
Language Modelling 13 1.64%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories