<style type="text/css">.wpb_animate_when_almost_visible{opacity:1}</style>

Keynote Speakers | 大会主讲人

BDAI2025 Keynote Speakers  
 
BDAI 2025 | August 22-24, 2025 | Xi 'an Jiaotong-Liverpool University, Taicang, China

Prof. Mengchu Zhou
New Jersey Institute of Technology, USA
周孟初教授, 美国新泽西理工学院

Fellow of IEEE, IFAC, AAAS, CAA and NAI

Biography: MengChu Zhou received his B.S. degree in Control Engineering from Nanjing University of Science and Technology, Nanjing, China in 1983, M.S. degree in Automatic Control from Beijing Institute of Technology, Beijing, China in 1986, and Ph. D. degree in Computer and Systems Engineering from Rensselaer Polytechnic Institute, Troy, NY in 1990. He joined the Department of Electrical and Computer Engineering, New Jersey Institute of Technology in 1990, and is now a Distinguished Professor. His interests are in intelligent automation, robotics, Petri nets, Internet of Things, edge/cloud computing, AI, and big data analytics. He has over 1400 publications including 17 books, over 900 journal papers including over 700 IEEE Transactions papers, 31 patents and 32 book-chapters. He is a recipient of Excellence in Research Prize and Medal from NJIT, Humboldt Research Award for US Senior Scientists from Alexander von Humboldt Foundation, and Franklin V. Taylor Memorial Award and the Norbert Wiener Award from IEEE Systems, Man, and Cybernetics Society, and Edison Patent Award from the Research & Development Council of New Jersey. He is a Highly-cited Scholar with over 81,000 GoogleScholar citations and h-index being 144. He is Fellow of IEEE, International Federation of Automatic Control (IFAC), American Association for the Advancement of Science (AAAS), Chinese Association of Automation (CAA) and National Academy of Inventors (NAI).

Title of Speech: Advancing Knowledge Distillation: A Multi-discipline Approach  

Abstract: Existing studies on knowledge distillation focus on teacher-centered methods, in which the teacher network is trained according to its own standards before transferring the learned knowledge to a student one. However, due to differences in network structure between teacher and student ones, the knowledge learned by the former may not be truly desired by the latter. Inspired by human educational wisdom, automatic control theory, and fuzzy logic concept, we propose a Student-Centered Distillation (SCD) method that enables the teacher network to adjust its knowledge transfer according to the student’s true needs. We implement it based on various human educational wisdom, e.g., the teacher network identifies and learns the knowledge desired by the student network on the validation set, and then transfers it to the latter through the training set. To address the problems of current deficiency knowledge, hard sample learning and knowledge forgetting faced by a student network in the learning process, we introduce and improve Proportional-Integral-Derivative (PID) algorithms from the field of automation to make them effective in identifying the current knowledge required by the student network. Furthermore, we propose a curriculum learning-based fuzzy logic strategy and apply it to the proposed PID control algorithm, such that the student network can actively pay attention to the learning of challenging samples. Experimental results show that SCD outperforms existing teacher-centered on knowledge distillation method in multiple computer vision tasks.  


Prof. Yingxu Wang
University of Calgary, Canada & Chongqing University of Science and Technology, China
王迎旭教授, 加拿大卡尔加里大学终身教授 & 重庆科技大学
重庆智能数学与自主智能研究院院长/首席科学家

IEEE Fellow

Biography: Prof. Yingxu Wang, FIEEE, FBCS, FI2CICC, FAAIA, FNYA, FWIF, P.Eng.; Professor emeritus, Dept. of ECE and Hotchkiss Brain Institute, Univ. of Calgary, Canada; Distinguished Chair Prof., Dean of Chongqing Research Institute of Intelligent Mathematics (IM) and Autonomous Intelligence (AI*), RI-IM.AI*; President of Int'l Institute of Cognitive Informatics and Cognitive Computing (I2CICC); Visiting Professors on sabbaticals at Stanford Univ. (2008|16), MIT (2012), UC Berkeley (2008), Oxford Univ. (1995|2018-23). Distinguished Visiting Professor at Tsinghua Univ. (2019-2022). Academic Committee Member of Tsinghua Beijing National Center of Information Science and Technology.
He received a PhD in Computer Science from Nottingham Trent University, UK in 1998, and has been a full professor since 1994. He is a distinguished chair professor of intelligent mathematics, intelligence science, brain science, and software science, Dean and Chief Scientist of CQRI-IM.AI*, and Honorary Chair of the University Academic Committee, Chongqing Univ. of Science and Technology (CQUST).
He has contributed to fundamental and transdisciplinary knowledge of AI*/IS/IM by: a) Formally proofing 100+ theorems in IM and IS; and b) Presenting 100+ invited keynote speeches in international conferences.

Title of Speech: On the Emergence of Autonomous AI (AI*): From Empirical Data Engineering to Rigorous Intelligent Science  

Abstract: This keynote presents the theoretical foundations of contemporary Intelligent Science (IS) underpinned by fundamental studies in Intelligent Mathematics (IM). It explains how empirical AI technologies will be matured towards IS driven by IM, that leads to the emergence of Autonomous AI (AI*). Advances in AI* underpinned by IM are revolutionarily transferring AI technologies from empirical training-based big-data engineering to contemporary IS embodied by IM-based machine intelligence generation. The AI* technology works autonomously without the need for pervasive empirical training, because rational proofs about the natural and the mental worlds can’t be merely derived by case-sensitive data or empirical instances, constrained by their unlimited domains and real-time constraints. The formal and fundamental studies on IS and IM have led to the revealment of the first axiom of IS and AI, i.e., “The theoretical foundation of AI is IS, while that of IS is IM , shortly: AI_IS_IM.
On the basis of the preceding causality, this keynote presents a scientific framework of IS underpinned by IM. The rigorous approach has provided a formal methodology for AI* system design and implementation. AI* and IM will theoretically and empirically improve traditional AI technologies, which are not only constrained by unbounded data scales and exponential complexity, but also unreasonable training energy consumption.