Institute of Robotics and Automatic Information System Tianjin Key Laboratory of Intelligent Robotics
Seminar Series：Advanced Robotics & Artificial Intelligence
报告题目：Foundations of AI: Machine Spaces for Universal Induction
报告人：Armin B. Cremers, B-IT, University of Bonn, Germany
Abstract: In the sixties Solomonoff introduced a universal induction scheme which eventually would learn every computable pattern in a data sequence.
Unfortunately, this generality comes at a price: the universal induction scheme is not computable, and within the asynchronous learning framework used by Solomonoff and followers the trade-off between universality and effectivity is, in fact, unavoidable. But if one changes the asynchronous learning framework into a synchronous one, i.e., one within which the time scales of the learning system and the data generating process are coupled, this trade-off will vanish and effective universal induction becomes possible. Axioms and metrics for realistic reference machine spaces are derived and related to advances in deep learning applications. (From joint work with J. Zimmermann)
Biography: Armin B. Cremers received his doctoral degree in mathematics and his lectureship qualification in computer science from the University of Karlsruhe (now KIT). He has served on the Computer Science Faculties of the University of Southern California, the University of Dortmund, and, since 1990, the University of Bonn as Head of the Artificial Intelligence / Robotics/ Intelligent Vision Systems Research Groups. In 2002 he became Founding Director of the Bonn-Aachen International Center for Information Technology (B-IT), Emeritus since 2014.