Coder Social home page Coder Social logo

gabrielfernandezfernandez / spivae Goto Github PK

View Code? Open in Web Editor NEW
6.0 1.0 0.0 19.28 MB

Stochastic processes insights from VAE. Code for the paper: Learning minimal representations of stochastic processes with variational autoencoders.

License: Apache License 2.0

Python 0.42% Jupyter Notebook 99.57% CSS 0.01%
anomalous-diffusion autoregressive-models brownian-motion feature-learning fractional-brownian-motion interpretability knowledge-discovery representation-learning stochastic-models time-series

spivae's Introduction

SPIVAE

Interpretable autoregressive β-VAE architecture.

SPIVAE is a machine learning method to study stochastic processes. It tries to learn the probability distribution of input trajectories and permits us to interpret its functioning and generate new trajectories with controllable features.

The approach was initially devised for the paper entitled Learning minimal representations of stochastic processes with variational autoencoders. We provide a documented library and detailed tutorials to facilitate the reproduction of our research findings.

Getting started

To use this code as a library, you will need a system with python>=3.10 and proceed with the installation. You can install SPIVAE by first cloning this repository in your file system:

git clone https://github.com/GabrielFernandezFernandez/SPIVAE.git
cd SPIVAE
pip install .

This will install all the necessary dependencies to make full use of the library. Make sure your file system has enough space to store the data files of some GBs.

Cite us

If you use this library, please give us credit.

@misc{fernandez2023learning,
  title = {Learning Minimal Representations of Stochastic Processes with Variational Autoencoders},
  author = {{Fern{\'a}ndez-Fern{\'a}ndez}, Gabriel and Manzo, Carlo and Lewenstein, Maciej and Dauphin, Alexandre and {Mu{\~n}oz-Gil}, Gorka},
  year = {2023},
  month = jul,
  number = {arXiv:2307.11608},
  eprint = {2307.11608},
  publisher = {{arXiv}},
  doi = {10.48550/arXiv.2307.11608},
  url = {http://arxiv.org/abs/2307.11608},
  keywords  = {Soft Condensed Matter (cond-mat.soft),
               Machine Learning (cs.LG),
               Biological Physics (physics.bio-ph),
               {Data Analysis, Statistics and Probability (physics.data-an)},
               Quantitative Methods (q-bio.QM)}
}

@misc{fernandez2023spivae,
  title = {{{SPIVAE}}},
  author = {{Fern{\'a}ndez-Fern{\'a}ndez}, Gabriel},
  year = {2023},
  month = jul,
  url = {https://github.com/GabrielFernandezFernandez/SPIVAE},
  urldate = {2023-07-21},
  copyright = {Apache-2.0}
}

spivae's People

Contributors

gabrielfernandezfernandez avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google ❤️ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.