Lecturer Profile |
Chen Junlong (C. L. Philip Chen), professor, vice chairman of the Automation Society, national thousand scholars, national special experts, vice president of the Macao Association of Science and Technology, professor of the University of Macao, former dean of the School of Science and Technology. Professor Chen is an IEEE Fellow (Institute / Fellow), American Association for the Advancement of Science AAAS Fellow (Institute / Fellow), International Pattern Recognition IAPRFellow (Institute / Fellow), Academician of the European Academy of Sciences, Academician of the European Academy of Sciences and Arts, International System and Fellow, Academician of the Institute of Cybernetics, Institute of Automation (CAA), and Hong Kong Institution of Engineers (HKIE) Fellow, currently the editor of the IEEE System of Human and Intelligent Society (IEEE Trans. on Systems, Man, and Cybernetics: Systems), formerly International President of the Society (2012-2013). Professor Chen's main research directions include intelligent systems and control, computational intelligence, hybrid intelligence, and data science. He is the world's highly cited scientist in the 2018 Clarivate Analytics 2018 computer science discipline. See https://orcid.org/0000-0001 for details. -5451-7230. He received his Distinguished Electrical and Computer Engineering Award from his alma mater, Purdue University, USA in 2016. In 2018 he received the Norbert Wiener Award for IEEE Systems Science Cybernetics. |
Lecture Abstract |
Deep learning has carved out a research wave in machine learning. With outstanding performance, more and more applications of deep learning in pattern recognition, image recognition, speech recognition, and video processing have been developed. The talk is to introduce “Broad Learning” – a complete paradigm shift in discriminative learning and a very fast and accurate learning without deep structure. The broad learning system (BLS) utilizes the power of incremental learning. That is without stacking the layer-structure, the designed neural networks expand the neural nodes broadly and update the weights of the neural networks incrementally when additional nodes are needed and when the input data entering to the neural networks continuously. The designed network structure and incremental learning algorithm are perfectly suitable for modeling and learning big data environment. Several BLS variations that cover existing deep-wide/broad-wide structures and their regression performance over function approximation, time series prediction, face recognition, and data modellingwill be discussed. |
