Advancing Efficient and Trustworthy AI for Science, Engineering, and Medicine

AI is touching every discipline and our daily lives. However, our current AI systems need to learn from massive amounts of data to be effective, and they can easily make surprisingly wrong, misleading decisions. In this talk, I'll describe my group's research in building the foundations and tools to enable AI systems to make reliable predictions, even if only limited data are available, and safeguard them against costly mistakes, leading to breakthroughs in AI's scientific, engineering, and medical applications.