Welcome to mcfly’s documentation!

The goal of mcfly is to ease using deep learning technology for time series classification and regression. The advantages of deep learning algorithms is that it can handle raw data directly with no need to compute signal features, it does not require a expert domain knowledge about the data, and it has been shown to be competitive with conventional machine learning techniques. As an example, you can apply mcfly on accelerometer data for activity classification, as shown in the mcfly tutorial.

If you use mcfly in your research, please cite the following software paper:

D. van Kuppevelt, C. Meijer, F. Huber, A. van der Ploeg, S. Georgievska, V.T. van Hees. Mcfly: Automated deep learning on time series. SoftwareX, Volume 12, 2020. doi: 10.1016/j.softx.2020.100548

Contents:

• Introduction
  • Licensing
• Installation
  • Visualization
• User Manual
  • Data preprocessing
  • Finding the best architecture
  • Visualize the training process
  • FAQ
• Technical documentation
  • Task inference
  • Hyperparameter search
  • Architectures
  • Other choices
  • Comparison with non-deep models

Reference

• mcfly
  • mcfly.models
  • mcfly.find_architecture module
  • mcfly.modelgen module

• Search Page