What does the future hold for computers and deep learning? Vladik Kreinovich, professor at the Department of Computing Science at the University of Texas discusses at an invited talk.
Seminar: From Traditional Neural Networks to Deep Learning and Beyond
Presented Vladik Kreinovich, professor at the Department of Computing Science at the University of Texas
Friday, November 17, 2017
Artisan Court at the Brickyard (BYAC) 110, Tempe campus [map]
How do we make computers think? To make machines that fly, it is reasonable to look at the creature that know how to fly: the birds. To make computers think, it is reasonable to analyze how we think. This the main origin of neural networks. At present, computer speed is rarely a problem, but accuracy is. This motivated deep learning. However, all this emulates only learning from examples, and we also learn by explicitly learning formulas and rules. How can we incorporate known formulas and rules into deep learning techniques?
In this talk, we describe what we and others have done already, and what (and how) we hope to achieve in the future.
About the speaker
Vladik Kreinovich received his MS in mathematics and computer science from St. Petersburg University, Russia, in 1974, and Ph.D. from the Institute of Mathematics, Soviet Academy of Sciences, Novosibirsk, in 1979. From 1975 to 1980, he worked with the Special Astrophysical Observatory with the Soviet Academy of Sciences.
For most of the 1980s, he worked on error estimation and intelligent information processing in Russia. Since 1990, he has worked in the Department of Computer Science at the University of Texas at El Paso. In addition, he has served as an invited professor in cities like Paris, Hanover, Hong Kong and Brazil.
His main interests are the representation and processing of uncertainty, especially interval computations and intelligent control. He has published six books, eighteen edited books and more than 1,300 papers. Kreinovich is a member of the editorial board of “Reliable Computing” and several other journals. In addition, he is the co-maintainer of the international website on interval computation.