Helps you find a suitable neural network configuration for deep learning on time series.


Cite this software

What mcfly can do for you

  • Provides starting point for researchers to use deep learning
  • Creates deep learning models for classification and regression on time series data
  • Derives features automatically from raw data
  • Helps with finding a suitable model architecture and hyperparameters
  • Has a tutorial in Python to get you started!

Deep learning is a powerful tool to help with automated classification or regression tasks. However, designing a deep learning network that works well for your data is not trivial: it requires the user to choose the number of layers in the network, the number of nodes in each layer, the type of each layer, and so forth. With so many degrees of freedom, finding the network that is right for your data is an arduous task. Moreover, each network still needs to be calibrated or trained before it can be usefully applied to automated classification or regression tasks.

mcfly simplifies this process by making explicit the required steps while offering useful default values at each step. mcfly then proceeds by trying out many different network configurations, training each one to the data provided by the user. It subsequently lists the performance of each network, along with a visualization that helps the user judge each network's tendency to overfit or underfit the data.

Logo of mcfly
Programming languages
  • JavaScript 75%
  • Python 16%
  • CSS 8%
  • HTML 1%
</>Source code

Participating organisations

Netherlands eScience Center

Reference papers


Mcfly: An easy-to-use tool for deep learning for time series classification

Author(s): Florian Huber
Published in 2020

mcfly: time series classification made easy

Author(s): Dafne van Kuppevelt
Published in 2017


Mcfly enabled us, for the first time, to forecast species distributions using entirely temporally explicit predictor data.
César Capinha, University of Lisbon


Jurriaan Spaaks
Netherlands eScience Center
Malte Lüken
Olga Lyashevska
Atze van der Ploeg
Netherlands eScience Center
Breixo Solino Fernandez
Netherlands eScience Center
Dafne van Kuppevelt
Dafne van Kuppevelt
Netherlands eScience Center
Florian Huber
Florian Huber
Netherlands eScience Center
Mateusz Kuzak
Netherlands eScience Center
Patrick Bos
Patrick Bos
Netherlands eScience Center
Vincent van Hees
Vincent van Hees
Netherlands eScience Center

Related projects

Predicting the Brugada ECG without ajmaline

Predicting the Brugada syndrome using machine learning

Updated 1 month ago


Early prediction of dyslexia in infants using machine learning

Updated 14 months ago

Googling the cancer genome

Identification and prioritization of cancer-causing structural variations in whole genomes

Updated 4 months ago