PhDAI 834 - Trustworthy and Explainable AI

Credit(s): 3 hours
This course focuses on the development of AI systems that are transparent, fair, and accountable, addressing critical challenges in trustworthiness and explainability. Students will explore concepts such as interpretable machine learning, fairness in algorithms, robustness against adversarial attacks, and ethical AI practices. Through case studies and projects, learners will develop skills to design AI models that balance high performance with transparency and reliability, ensuring their suitability for deployment in sensitive and high-stakes domains like healthcare, finance, and law.