Day 1 – Introduction to XAI:
Theme: An Overview of XAI Methods, Forms, and Frameworks
- XAI Methods and Their Classifications.
- Forms of Explanation.
- Frameworks for Model Interpretability and Explanation.
- Knowledge extraction methods.
- Result visualization methods.
Theme: Data-centric approaches
- Introduction to data-centric XAI.
- Thorough data analysis and profiling process.
- Monitoring and anticipating drifts.
- Checking adversarial robustness.
- Measuring data forecast ability.
Day 2 – Trustworthy, Explainable Systems, and Industry Best Practices:
Theme: Explainable and Trustworthy Multi-modal XAI
- Large language models and their generative power for Multi-modal XAI.
- Validating interpretability, explainability, and trustworthiness of Multi-modal XAI systems.
- Guidelines for auditing Multi-modal XAI systems in compliance with standards and regulations..
Theme: XAI Industry Best Practices
- Open challenges of XAI
- Guidelines for designing explainable ML systems.
- Adopting a data-first approach for explainability.
- Emphasizing IML for explainability.
- Emphasizing prescriptive insights for explainability.
- Post-course roadmap, reflection checklist, and certificate ceremony
Benefits for course participants
- Grasp the importance of Explainable Artificial Intelligence (XAI) and understand how it shapes trust, accountability, and decision-making across diverse professional domains.
- Master the key theories and principles of explainability, exploring how transparency and interpretability are achieved in AI systems.
- Apply practical XAI techniques through hands-on experimentation with real-world datasets and Jupyter notebooks, focusing on domains such as healthcare, finance, and logistics.
- Analyze the interplay between XAI, fairness, bias, and transparency, using computational experiments to evaluate ethical and performance trade-offs.
- Critically assess the legal, ethical, and societal dimensions of XAI, developing an informed perspective on responsible AI governance and deployment.
