As machine learning models grow increasingly complex, the ability to interpret, explain, and justify their predictions becomes critical for trust, accountability, regulatory compliance, and scientific understanding. This course equips students with the concepts, tools, and techniques needed to build and evaluate explainable data science systems.
Modern AI systems influence high-stakes decisions in healthcare, finance, hiring, law enforcement, and more. Without explainability, these systems risk embedding bias, eroding trust, and violating emerging regulations such as the EU AI Act and GDPR's "right to explanation." This course treats explainability not as an afterthought, but as a core design principle.
- Teacher: Kaung Hein Htet
- Teacher: Sein Minn