Rational Activations - Learnable Rational Activation Functions
First introduce as PAU in Padé Activation Units: End-to-end Learning of Activation Functions in Deep Neural Network.
1. About Rational Activation Functions
Rational Activations are a novel learnable activation functions. Rationals encode activation functions as rational functions, trainable in an end-to-end fashion using backpropagation and can be seemingless integrated into any neural network in the same way as common activation functions (e.g. ReLU).
Rationals: Beyond known Activation Functions
Rational can approximate any known activation function arbitrarily well (cf. Padé Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks): 
(*the dashed lines represent the rational approximation of every function)
Rational are made to be optimized by the gradient descent, and can discover good properties of activation functions after learning (cf Recurrent Rational Networks): 
Rationals evaluation on different tasks
-
They were first applied (as Padé Activation Units) to Supervised Learning (image classification) in Padé Activation Units:....
See rational_sl github repo
Rational matches or outperforms common activations in terms of predictive performance and training time. And, therefore relieves the network designer of having to commit to a potentially underperforming choice.
- Recurrent Rational Functions have then been introduced in Recurrent Rational Networks, and both Rational and Recurrent Rational Networks are evaluated on RL Tasks.
See rational_rl github repo
2. Dependencies
We support MxNet, Keras, and PyTorch. Instructions for MxNet can be found here. Instructions for Keras here. The following README instructions assume that you want to use rational activations in PyTorch.
PyTorch>=1.4.0
CUDA>=10.2
3. Installation
To install the rational_activations module, you can use pip, but:
rational_activations is currently compatible with torch==1.9.0 by default
For non TensorFlow and MXNet users, or if the command bellow don't work the package listed bellow don't work on your machine:
TensorFlow or MXNet (and torch==1.9.0)
pip3 install -U pip wheel
pip3 install torch rational_activations
Other CUDA/Pytorch
For any other torch version, please install from source: Modify requirements.txt to your corresponding torch version
pip3 install airspeed # to compile the CUDA templates
git clone https://github.com/ml-research/rational_activations.git
cd rational_activations
pip3 install -r requirements.txt --user
python3 setup.py install --user
If you encounter any trouble installing rational, please contact this person.
4. Using Rational in Neural Networks
Rational can be integrated in the same way as any other common activation function.
import torch
from rational.torch import Rational
model = torch.nn.Sequential(
torch.nn.Linear(D_in, H),
Rational(), # e.g. instead of torch.nn.ReLU()
torch.nn.Linear(H, D_out),
)
Please also check the documentation
5. Cite Us in your paper
@inproceedings{molina2019pade,
title={Pad{\'e} Activation Units: End-to-end Learning of Flexible Activation Functions in Deep Networks},
author={Molina, Alejandro and Schramowski, Patrick and Kersting, Kristian},
booktitle={International Conference on Learning Representations},
year={2019}
}
@article{delfosse2021recurrent,
title={Recurrent Rational Networks},
author={Delfosse, Quentin and Schramowski, Patrick and Molina, Alejandro and Kersting, Kristian},
journal={arXiv preprint arXiv:2102.09407},
year={2021}
}
@misc{delfosse2020rationals,
author = {Delfosse, Quentin and Schramowski, Patrick and Molina, Alejandro and Beck, Nils and Hsu, Ting-Yu and Kashef, Yasien and Rüling-Cachay, Salva and Zimmermann, Julius},
title = {Rational Activation functions},
year = {2020},
publisher = {GitHub},
journal = {GitHub repository},
howpublished={\url{https://github.com/ml-research/rational_activations}}
}
21 Aug 23, 2022
181 Nov 18, 2022
261 Dec 31, 2022
0 Jul 15, 2021
47 Dec 23, 2022
184 Dec 27, 2022
178 Jan 5, 2023
43 Jan 5, 2023
6.6k Jan 6, 2023
40 Dec 27, 2022
5 Jan 18, 2022
4 Dec 3, 2022
35 Jan 6, 2023
1 Feb 23, 2022
3 Aug 17, 2022
10 Jan 2, 2023
113 Dec 27, 2022
4.3k Jan 8, 2023
32 Nov 20, 2022