Patch Learning: A New Method of Machine Learning, Implemented by Means of Fuzzy Sets
Jerry M. Mendel
There have been different strategies to improve the performance of a machine learning model, e.g., increasing the depth, width, and/or nonlinearity of the model, and using ensemble learning to aggregate multiple base/weak learners in parallel or in series. This talk describes a novel and new strategy called patch learning (PL) for this problem. It consists of three steps: 1) train an initial global model using all training data; 2) identify from the initial global model the patches which contribute the most to the learning error, and then train a (local) patch model for each such patch; and, 3) update the global model using training data that do not fall into any patch. To use a PL model, one first determines if the input falls into any patch. If yes, then the corresponding patch model is used to compute the output. Otherwise, the global model is used. To-date, PL can only be implemented using fuzzy systems. How this is accomplished will be explained. Finally, some regression problems on 1D/2D/3D curve fitting, nonlinear system identification, and chaotic time-series prediction, will be explained to demonstrate the effectiveness of PL. PL opens up a promising new line of research in machine learning.
Jerry M. Mendel (LF’04) received the Ph.D. degree in electrical engineering from the Polytechnic Institute of Brooklyn, Brooklyn, NY. Currently, he is Emeritus Professor of Electrical Engineering at the University of Southern California in Los Angeles. He has published over 580 technical papers and is author and/or co-author of 13 books, including Uncertain Rule-based Fuzzy Systems: Introduction and New Directions, 2nd ed., Perceptual Computing: Aiding People in Making Subjective Judgments, and Introduction to Type-2 Fuzzy Logic Control: Theory and Application. He is a Life Fellow of the IEEE, a Distinguished Member of the IEEE Control Systems Society, and a Fellow of the International Fuzzy Systems Association. He was President of the IEEE Control Systems Society in 1986, a member of the Administrative Committee of the IEEE Computational Intelligence Society for nine years, and Chairman of its Fuzzy Systems Technical Committee and the Computing With Words Task Force of that TC. Among his awards are the 1983 Best Transactions Paper Award of the IEEE Geoscience and Remote Sensing Society, the 1992 Signal Processing Society Paper Award, the 2002 and 2014 Transactions on Fuzzy Systems Outstanding Paper Awards, a 1984 IEEE Centennial Medal, an IEEE Third Millenium Medal, a Fuzzy Systems Pioneer Award (2008) from the IEEE Computational Intelligence Society. His present research interests include: type-2 fuzzy logic systems and computing with words.
China Mobile’s Exploration and Practice on Intelligent Network
Huang Yuhong, Deputy General Manger of China Mobile Research Institute. She is responsible for mobile network technology research, standardization and specification, test and trial, industry technology cooperation etc. She has participated in several important projects such as of GSM900/1800, GPRS/EDGE, WLAN, 3G, 4G, 5G. Now she also leads the technology research and standardization of 5G evolution and beyond. She used to be vice chair of 3GPP SA and now is board Member of O-RAN and board member of NGMN and the Secretary-General of Global TD-LTE Initiative (GTI).
China Mobile’s Exploration and Practice on Intelligent Network
This speech will introduce China Mobile’s exploration and practice on Intelligent Network. There will be four parts. The first part will be the top level design consideration of intelligent network, including e2e architecture and high level idea and target. The second part will be China Mobile’s activities on standardization and open source for intelligent network. The third part will be some application case of China Mobile’s practice on intelligent network. The last part will be suggestions on global cooperation to realize the successful development of intelligent network.
Title: Machine Learning in Brain-Computer Interfaces
A brain-computer interface (BCI) enables a user to communicate with a computer directly using brain signals. Electroencephalograms (EEGs) used in BCIs are weak, easily contaminated by interference and noise, non-stationary for the same subject, and varying across different subjects and sessions. Thus, sophisticated machine learning approaches are needed for accurate and reliable EEG-based BCIs. This talk will introduce the basic concepts of BCIs, review the latest progress, and describe several newly proposed machine learning approaches for BCIs.
Dongrui Wu received a B.E in Automatic Control from the University of Science and Technology of China, Hefei, China, in 2003, an M.Eng in Electrical and Computer Engineering from the National University of Singapore in 2005, and a PhD in Electrical Engineering from the University of Southern California, Los Angeles, CA, in 2009. He is now a Professor and Deputy Director of the Key Laboratory of the Ministry of Education for Image Processing and Intelligent Control, School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China.
Prof. Wu's research interests include affective computing, brain-computer interface, computational intelligence, and machine learning. He has more than 140 publications (6,400+ Google Scholar citations; h=39), including a book "Perceptual Computing" (Wiley-IEEE Press, 2010), and five US patents. He received the FUZZ-IEEE Best Student Paper Award in 2005, the IEEE Computational Intelligence Society (CIS) Outstanding PhD Dissertation Award in 2012, the IEEE Transactions on Fuzzy Systems Outstanding Paper Award in 2014, the North American Fuzzy Information Processing Society (NAFIPS) Early Career Award in 2014, the IEEE Systems, Man and Cybernetics (SMC) Society Early Career Award in 2017, and the IEEE SMC Society Best Associate Editor Award in 2018. He was a finalist of the IEEE Transactions on Affective Computing Most Influential Paper Award in 2015, the IEEE Brain Initiative Best Paper Award in 2016, the 24th International Conference on Neural Information Processing Best Student Paper Award in 2017, the Hanxiang Early Career Award in 2018, and the USERN Prize in Formal Sciences in 2019. He was a selected participant of the Heidelberg Laureate Forum in 2013, the US National Academies Keck Futures Initiative (NAKFI) in 2015, and the US National Academy of Engineering German-American Frontiers of Engineering (GAFOE) in 2015. His team won the First Prize of the China Brain-Computer Interface Competition in 2019.
Prof. Wu is/was an Associate Editor of the IEEE Transactions on Fuzzy Systems (2011-2018), the IEEE Transactions on Human-Machine Systems (since 2014), the IEEE Computational Intelligence Magazine (since 2017), and the IEEE Transactions on Neural Systems and Rehabilitation Engineering (since 2019).
Topic: Huawei AI strategy and Innovation: Ascend AI solution
In Oct 2018, Huawei announced its AI strategy, after 18 months, how about it is going now? We will retrospect the its major progress and innovation in recent years and look forward its future. The major progress and innovation includes : The innovation of AI serials processors with common DaVinci core; develop Atlas AI computing solution offering serials AI infrastructure for all-scenario AI application; development operators for CANN (Compute Architecture for Neural Networks) operator library to better match the Ascend chip enablement; delivery MindSpore to support all-scenario deep learning framework that best manifests the computing power of the Ascend AI processor, provides development experience with friendly design and efficient execution for the data; Innovation ModelArts for algorithm development, machine annotation, model training, and algorithm generation. These all make AI modeling more efficient and effective.
Chief Engineering of Shanghai R&D Center of Huawei
Advanced Manager of Huawei kunpeng & Ascend Technology Ecology
Director of 5G Joint Innovation & Verification Center
Working in Huawei, Alcatel Lucent/ Alcatel for 20 Years.
System Dynamics Modeling Expert, the vice director of System Dynamics Society of China
Ph.D. of Management Science, Master Degree of Physics at Fudan University, Bachelor of Engineering Physics at Tsinghua University