/LionLearn

A library of techniques for local interpretation of machine learning models

Primary LanguageJupyter NotebookGNU General Public License v3.0GPL-3.0

LioNets Version 2 is out now

LionLearn

LionLearn

A library providing techniques for local interpretation of machine learning models

This library will provide ways to local explain machine learning models like random forests, neural networks, etc. Every technique of this library will be model-specific and local-based. Currently there are the following two approaches available:

  1. LioNets: Local Interpretation Of Neural nETworkS through penultimate layer decoding
  2. LioNets V2: LioNets: A Neural-Specific Local Interpretation Technique Exploiting Penultimate Layer Information
  3. LionForests: Conclusive Local Interpretation Rules for Random Forests
  4. Preliminary LionForests: Local Interpretation Of raNdom FORESts through paTh Selection
  5. Multi LionForests: Local Multi-Label Explanations for Random Forest

Other related work of us:

  1. Altruist: Argumentative Explanations through Local Interpretations of Predictive Models
  2. VisioRed: Interactive UI Tool for Interpretable Time Series Forecasting called VisioRed

This project is supported by the European Union's Horizon 2020 research and innovation programme under grant agreement No 825619, AI4EU Project.

Developed by

Name Email
Ioannis Mollas iamollas@csd.auth.gr
Nikolaos Mylonas myloniko@csd.auth.gr
Grigorios Tsoumakas greg@csd.auth.gr
Nick Bassiliades nbassili@csd.auth.gr