All Projects → msmbuilder → Vde

msmbuilder / Vde

Licence: mit
Variational Autoencoder for Dimensionality Reduction of Time-Series

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Vde

Tsmoothie
A python library for time-series smoothing and outlier detection in a vectorized way.
Stars: ✭ 109 (-26.35%)
Mutual labels:  jupyter-notebook, time-series
Normalizing Flows
Understanding normalizing flows
Stars: ✭ 126 (-14.86%)
Mutual labels:  jupyter-notebook, variational-autoencoder
Vae Tensorflow
A Tensorflow implementation of a Variational Autoencoder for the deep learning course at the University of Southern California (USC).
Stars: ✭ 117 (-20.95%)
Mutual labels:  jupyter-notebook, variational-autoencoder
Btctrading
Time Series Forecast with Bitcoin value, to detect upward/down trends with Machine Learning Algorithms
Stars: ✭ 99 (-33.11%)
Mutual labels:  jupyter-notebook, time-series
Openff Toolkit
The Open Forcefield Toolkit provides implementations of the SMIRNOFF format, parameterization engine, and other tools. Documentation available at http://open-forcefield-toolkit.readthedocs.io
Stars: ✭ 138 (-6.76%)
Mutual labels:  jupyter-notebook, molecular-dynamics
Dmm
Deep Markov Models
Stars: ✭ 103 (-30.41%)
Mutual labels:  jupyter-notebook, time-series
Kaggle Web Traffic
1st place solution
Stars: ✭ 1,641 (+1008.78%)
Mutual labels:  jupyter-notebook, time-series
Pycon Ua 2018
Talk at PyCon UA 2018 (Kharkov, Ukraine)
Stars: ✭ 60 (-59.46%)
Mutual labels:  jupyter-notebook, time-series
Deep Learning With Python
Example projects I completed to understand Deep Learning techniques with Tensorflow. Please note that I do no longer maintain this repository.
Stars: ✭ 134 (-9.46%)
Mutual labels:  jupyter-notebook, variational-autoencoder
Stldecompose
A Python implementation of Seasonal and Trend decomposition using Loess (STL) for time series data.
Stars: ✭ 130 (-12.16%)
Mutual labels:  jupyter-notebook, time-series
Online Recurrent Extreme Learning Machine
Online-Recurrent-Extreme-Learning-Machine (OR-ELM) for time-series prediction, implemented in python
Stars: ✭ 95 (-35.81%)
Mutual labels:  jupyter-notebook, time-series
Scipy con 2019
Tutorial Sessions for SciPy Con 2019
Stars: ✭ 142 (-4.05%)
Mutual labels:  jupyter-notebook, time-series
Stingray
Anything can happen in the next half hour (including spectral timing made easy)!
Stars: ✭ 94 (-36.49%)
Mutual labels:  jupyter-notebook, time-series
Time Series Forecasting With Python
A use-case focused tutorial for time series forecasting with python
Stars: ✭ 105 (-29.05%)
Mutual labels:  jupyter-notebook, time-series
Bayesian Machine Learning
Notebooks about Bayesian methods for machine learning
Stars: ✭ 1,202 (+712.16%)
Mutual labels:  jupyter-notebook, variational-autoencoder
Deeptime
Deep learning meets molecular dynamics.
Stars: ✭ 123 (-16.89%)
Mutual labels:  jupyter-notebook, time-series
Mckinsey Smartcities Traffic Prediction
Adventure into using multi attention recurrent neural networks for time-series (city traffic) for the 2017-11-18 McKinsey IronMan (24h non-stop) prediction challenge
Stars: ✭ 49 (-66.89%)
Mutual labels:  jupyter-notebook, time-series
Vae protein function
Protein function prediction using a variational autoencoder
Stars: ✭ 57 (-61.49%)
Mutual labels:  jupyter-notebook, variational-autoencoder
Simplestockanalysispython
Stock Analysis Tutorial in Python
Stars: ✭ 126 (-14.86%)
Mutual labels:  jupyter-notebook, time-series
Data science blogs
A repository to keep track of all the code that I end up writing for my blog posts.
Stars: ✭ 139 (-6.08%)
Mutual labels:  jupyter-notebook, time-series

Variational Dynamical Encoder (VDE)

Often the analysis of time-dependent chemical and biophysical systems produces high-dimensional time-series data for which it can be difficult to interpret which features are most salient in defining the observed dynamics. While recent work from our group and others has demonstrated the utility of time-lagged co-variate models to study such systems, linearity assumptions can limit the compression of inherently nonlinear dynamics into just a few characteristic components. Recent work in the field of deep learning has led to the development of variational autoencoders (VAE), which are able to compress complex datasets into simpler manifolds. We present the use of a time-lagged VAE, or variational dynamics encoder (VDE), to reduce complex, nonlinear processes to a single embedding with high fidelity to the underlying dynamics. We demonstrate how the VDE is able to capture nontrivial dynamics in a variety of examples, including Brownian dynamics and atomistic protein folding. Additionally, we demonstrate a method for analyzing the VDE model, inspired by saliency mapping, to determine what features are selected by the VDE model to describe dynamics. The VDE presents an important step in applying techniques from deep learning to more accurately model and interpret complex biophysics.

Requirements

  • numpy
  • pytorch
  • msmbuilder

Usage

Using the VDE is as easy as using any msmbuilder model:

from vde import VDE
from msmbuilder.example_datasets import MullerPotential

trajs = MullerPotential().get().trajectories

lag_time = 10
vde_mdl = VDE(2, lag_time=lag_time, hidden_layer_depth=3,
          sliding_window=True, cuda=True, n_epochs=10,
          learning_rate=5E-4)

latent_output = vde_mdl.fit_transform(trajs)

Cite

If you use this code in your work, please cite:

@article{PhysRevE.97.062412,
  title = {Variational encoding of complex dynamics},
  author = {Hern\'andez, Carlos X. and Wayment-Steele, Hannah K. and Sultan, Mohammad M. and Husic, Brooke E. and Pande, Vijay S.},
  journal = {Phys. Rev. E},
  volume = {97},
  issue = {6},
  pages = {062412},
  numpages = {11},
  year = {2018},
  month = {Jun},
  publisher = {American Physical Society},
  doi = {10.1103/PhysRevE.97.062412},
  url = {https://link.aps.org/doi/10.1103/PhysRevE.97.062412}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].