EXPLAINABILITY OF AI - IBM
Selected applicants will have the chance to attend an interactive workshop held by Dennis Wei (IBM Research) on explainability of AI (XAI). Participants will learn about most recent developments in XAI and get hands-on experience on AI Explainability 360, an open source software toolkit that showcases how machine learning models predict labels by various means, throughout the AI application lifecycle. The toolkit features ten diverse and state-of-the-art explainability methods and two evaluation metrics. More info at this website and in this paper.
Dennis Wei is a Research Staff Member in the Trusted AI department, IBM Research AI at the Thomas J. Watson Research Center. His current interests center around trustworthy machine learning, including interpretability of machine learning models, algorithmic fairness, causal inference and graphical models, and data science for social good. He received S.B. degrees in electrical engineering and in physics in 2006, the M.Eng. degree in electrical engineering in 2007, and the Ph.D. degree in electrical engineering in 2011, all from MIT. Dennis was a co-winner of the FICO Explainable Machine Learning Challenge in 2018
With more than 3,000 researchers across the globe, IBM Research is committed to catalyze and drive the advancements in science and technology. AI Explainability 360 was created by IBM Research and donated by IBM to the Linux Foundation AI & Data.