High-performing AI models are not always trustworthy. This session explores how Explainable AI (XAI) techniques such as Grad-CAM, LIME, and Saliency Maps help uncover the reasoning behind model predictions. Through practical examples and real-world case studies, participants will learn how to interpret AI decisions, identify potential biases, and build more transparent and reliable AI systems. Ideal for developers and AI practitioners looking to move beyond accuracy and toward trustworthy AI.

with Asma Merabet

👩‍🎓 Doctor in Artificial Intelligence

⭐ Google Developer Expert (AI)

💻 Backend Developer at DeepMind

🌍 GDG Setif Organizer

As AI systems become increasingly integrated into our daily lives, understanding why a model makes a decision is becoming just as important as the decision itself.

In this session, we'll explore practical Explainable AI (XAI) techniques, including:

🔍 Grad-CAM

🔍 LIME

🔍 Saliency Maps

Through real-world examples and case studies, you'll learn how to:

✅ Interpret AI predictions

✅ Detect biases and hidden risks

✅ Build more transparent AI systems

✅ Move beyond accuracy toward trustworthy AI

Whether you're an AI practitioner, developer, researcher, or simply passionate about responsible AI, this session is for you.