报告题目：On Actional-Perceptual Causality – Concepts and Inductive Learning for AI and Robotics
报告时间：3月12日（周二）下午2：00
报告地点：学科3号楼S410会议室
报告人：Seng-Beng Ho教授
主持人：刘青山 教授
欢迎广大师生踊跃参加！
江苏省大数据分析技术重点实验室
江苏省气象能源利用与控制工程技术研究中心
江苏省大气环境与装备技术协同创新中心
自动化学院
2018年3月7日
Abstract: Causal learning in AI and robotics has not received the same attention as deep learning and reinforcement learning. This talk attempts to promote a consensus among researchers in AI and robotics a fundamental framework within which to conduct research on inductive perceptual causal learning, i.e., learning causality from sensory data - specifically from perceptual data of an AI or robotic system observing and interacting with the environment. Because actions are a critical aspect of establishing causality for robotic systems, the term actional-perceptual causality is used to emphasize their importance. Using a distinction between diachronic (over time) and synchronic (timeless, contextual) conditions to characterize the causal preconditions involved in an actional-perceptual situation, a framework of inductive causal learning for AI and robotics can be made equivalent to the well-established and sound statistical method of causal learning used in experimental sciences, thereby placing actional-perceptual causal learning for AI and robotics on a firm foundation. A causal learning and planning framework that is able to achieve human-like performance in terms of the short time taken to learn to play the Atari game Space Invaders will be described. This represents a 10,000 times speed-up compared with the time needed to learn to play the game using deep reinforcement learning.
Biography: Seng-Beng Ho obtained his Ph.D. in Cognitive Science (AI, Neuroscience, Psychology, and Linguistics) and M.Sc. in Computer Science from the University of Wisconsin, Madison, U.S.A. He has a B.E. in Electronic Engineering from the University of Western Australia. For 11 years, he was President of E-Book Systems Pte Ltd, a company he founded that developed and marketed a novel 3D page-flipping interface for electronic books, with offices in the Silicon Valley, Beijing, Tokyo, Germany, and Singapore. Prior to that, he was a lecturer at the Department of Information Systems and Computer Science, National University of Singapore. He returned from industry to research institutes to conduct fundamental AI research 10 years ago and is currently Senior Scientist and Deputy Director of the Department of Social and Cognitive Computing at the Institute of High Performance Computing, A*STAR, Singapore. He is the sole author of a monograph published in June 2016 by Springer International entitled “Principles of Noology: Toward a Theory and Science of Intelligence”. In the book, he presents a principled and fundamental theoretical framework that is critical for building truly general AI systems. He holds 36 U.S. and world-wide patents related to e-book technology.
