Trustworthy Machine Learning and Artificial Intelligence - Episode 6

Explore the multifaceted landscape of trustworthy artificial intelligence in this 46-minute podcast episode featuring Dr. Kush Varshney, an IBM Fellow and globally recognized expert in trustworthy machine learning, interviewed by Dr. Lav Varshney from the University of Illinois Urbana-Champaign. Discover the core principles that make AI systems not only accurate but also fair, robust, explainable, transparent, inclusive, and beneficial. Learn how Dr. Varshney distinguishes trustworthy AI from related concepts such as AI ethics, AI safety, and responsible AI, while understanding how signal processing techniques like Boolean compressed sensing, continued fraction representations, and short-time Fourier transforms inform his research approach. Examine the societal impact of AI systems and the critical shift toward generative and agentic models that are reshaping the field. Gain insights into the importance of governance and policy frameworks for AI deployment, and explore new research directions aimed at building more empowering and accountable AI systems. Understand the practical applications of trustworthy AI through discussion of widely-used toolkits like AI Fairness 360 and AI Explainability 360, developed by Dr. Varshney and his team at IBM Research.