Topic: Reasoning on Uncertain Learned Data
This basic question faces humans in everyday experience. It is also an important technological problem if we are to make good use of the power of machine learning. In this talk this question will be discussed in the framework of a new theory of human capabilities for information processing.
Leslie Valiant was educated at King's College, Cambridge, Imperial College London, and the University of Warwick, where he received a PhD in computer science in 1974. He won the Turing Award in 2010 with a citation that reads, "For transformative contributions to the theory of computation, including the theory of probably approximately correct (PAC) learning, the complexity of enumeration and of algebraic computation, and the theory of parallel and distributed computing." Other accolades include the Nevanlinna Prize in 1986, the Knuth Prize in 1997, and the EATCS Award in 2008. He was elected a Fellow of the Royal Society (FRS) in 1991, a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI) in 1992, and a member of the United States National Academy of Sciences in 2001.