Machine learning pioneer to speak today at KU

LAWRENCE — Vladimir Vapnik, a pioneer in machine learning (ML), will speak at 2 p.m. today, Sept. 13, in Nichols Hall as part of the new Bold Aspirations Visitor and Lecture series. The event is free and open to the public.

Vapnik, a member of the U.S. National Academy of Engineering, fellow at NEC Laboratories and professor of computer science at Columbia University, will present "Learning with Nontrivial Teacher: Learning Using Privileged Information (LUPI)." By including explanations, comments and other teaching elements with example data, Vapnik's group is aiming to reduce training time for ML applications that derive meaning from huge amounts of disorganized data.

Machine learning is used everywhere from facial recognition and credit card fraud detection to customized user profiles and medical diagnoses. It extracts important patterns and trends from massive data sets being generated in medicine, finance, industry and other fields. ML tools require training using test data sets — everything from videos on YouTube to credit card statements. They learn what to look for and how to incorporate new data and adapt accordingly, improving performance over time.

Vapnik established the foundation for the modern machine learning theory with the Vapnik-Chervonenkis theory (VC theory), which uses statistical and mathematical methods to explain the learning process. He continued building on the VC theory, finally inventing the concept of the support vector machine (SVM), which identifies and predicts patterns and classifies data.

A host of honors have been presented to Vapnik. He was inducted into the U.S. National Academy of Engineering in 2006. He received the 2005 Gabor Award, the 2008 Paris Kanellakis Award, the 2010 Neural Networks Pioneer Award, the 2012 IEEE Frank Rosenblatt Award and the 2012 Benjamin Franklin Medal in Computer and Cognitive Science. He was born in the Soviet Union and received his master's degree in mathematics at the Uzbek State University, Samarkand, Uzbek in 1958 and a doctorate in statistics at the Institute of Control Sciences, Moscow in 1964.

The lecture series is sponsored by the Office of the Provost in order to bring nationally and internationally prominent scientists to campus, build collaborations and recruit stellar faculty. It is co-sponsored by the Information and Telecommunication Technology Center and the Department of Electrical Engineering and Computer Science.

For more information, contact the Office of the Provost at (785) 864-4904.