Conference Banner

Explainability & Interpretability in ML

Scientific Session

Explainability & Interpretability in ML

Explainability & Interpretability in ML:

Making ML models understandable and trustworthy.
Techniques: SHAP, LIME, Decision Trees visualization.
Applications: AI in healthcare, finance, and law where decisions need justification.

Sub Tracks:
Model-Specific Interpretability
Model-Agnostic Interpretability
Fairness, Bias Detection & Ethical AI
Explainable Deep Learning

Watsapp