An AI Tool for Explainable AI

  by   Hassan Eshkiki






Departments Computer Science
DescriptionSwansea University has introduced ExMed, a powerful tool designed to facilitate Explainable AI (XAI) data analytics for domain experts without the need for explicit programming skills. ExMed supports data analytics with multiple feature attribution algorithms, providing clear explanations for machine learning classifications and regressions. We are excited to relaunch this project as a learning platform for students, enabling them to experience machine learning without any coding requirements. Our goal is to develop robust software capable of handling data preparation, data visualization, and demonstrating the application of machine learning in real-world scenarios. In addition to its existing capabilities, ExMed now includes features for automated experiments, diverse model training, and model development. Users can leverage pre-built models and create pipelines with no coding, significantly reducing the need for in-depth machine learning knowledge. We aim to keep ExMed open-source, customizable, and modular, allowing for continuous improvement and adaptation. Furthermore, ExMed’s explainable AI features will be expanded with additional models to enhance its analytical capabilities.
PreparationIt is suggested to read: Eshkiki, Hassan, Marcin Kapcia, Jamie Duell, Xiuyi Fan, Shangming Zhou, and Benjamin Mora. "ExMed: An AI Tool for Experimenting Explainable AI Techniques On Medical Data Analytics." 2021 IEEE 33rd International Conference On Tools With Artificial Intelligence (ICTAI) 2021: 841-845. Microsoft. “Tutorial: Train Your First Machine Learning Model - Automated ML.” Microsoft Learn, 2024, https://learn.microsoft.com/en-us/azure/machine-learning/tutorial-first-experiment-automated-ml?view=azureml-api-2.
Project Categories Artificial Intelligence (AI), Data Science
Project Keywords Machine Learning, Neural Networks


Level of Studies

Level 6 (Undergraduate Year 3) yes
Level 7 (Masters) yes
Level 8 (PhD) yes