Explainable Artificial Intelligence methods (XAI) represent methods to understand and interpret machine learning (ML) methods, and have recently received a lot of attention. In this project, we will explore the potential of using XAI to improve the prediction performance of ML methods.
XAI methods are able to point to the most important variables of a ML model, or to the most important parts of the input data (such as images) when performing predictions. In this project we will explore the potential of using such XAI information to improve the prediction performance of the machine learning models. For example by retraining the ML model, putting more emphasis (or maybe less) on the variables of parts of the input that were important for the prediction.
Goal
Develop methods that use XAI to potentially improve ML prediction performance.
Learning outcome
- Machine learning
- Explainable Artificial Intelligence
- Real-world applications
Qualifications
- Python programming
- Knowledge about machine learning is an advantage
Supervisors
- Hugo Hammer
- Michael Riegler
References
- Molnar, C. (2020). Interpretable machine learning. Lulu. com.
