This repository contains the tool for interactive editing, evolution and visualization of the composite machine learning models obtained with FEDOT AutoML Framework. The online version this tool is available in https://fedot.onti.actcognitive.org/

• Tutorial for beginners
• Tutorial for advanced users (local run)

Description of several domain-specific cases that can be sovled using composite pipelines

Detailed description of domain case, pipeline and its paramaters for specified case

Interactive editor of the pipeline structure. All nodes, edges, and hyperparameters can be changed.

Analytics for the current pipeline and its history of evolution.

The visualisation of the evolution history.

Open-source AutoML framework FEDOT

We acknowledge the contributors for their important impact and the participants of the numerous scientific conferences and workshops for their valuable advice and suggestions.

Telegram channel for solving problems and answering questions on FEDOT and FEDOT.Web

Natural System Simulation Team

Newsfeed

Youtube channel

@article{nikitin2021automated, title = {Automated evolutionary approach for the design of composite machine learning pipelines}, author = {Nikolay O. Nikitin and Pavel Vychuzhanin and Mikhail Sarafanov and Iana S. Polonskaia and Ilia Revin and Irina V. Barabanova and Gleb Maximov and Anna V. Kalyuzhnaya and Alexander Boukhanovsky}, journal = {Future Generation Computer Systems}, year = {2021}, issn = {0167-739X}, doi = {https://doi.org/10.1016/j.future.2021.08.022}}