A Dynamic Neural Network Structure and its Application for Continuous Learning in an Open Environment

Host:            Prof. Ye Shi

Link:                Tencent:     https://meeting.tencent.com/dm/9DQo9TPiQWbn

Abstract:    Learning in neural networks suffers from the fixed structure of the network with a given number of layers and neurons when gather information for training. In this talk, a dynamic neural network structure via Stacked Broad Learning Systems (BLS) will be discussed. The BLS has been proved to be effective and efficient lately. The proposed dynamic model is a novel incremental stacking of BLS. This invariant inherits the efficiency and effectiveness of BLS that the structure and weights of lower layers of BLS are fixed when the new blocks are added. The modified incremental stacking algorithm only computes the connection weights within the BLS block while the connecting weights of the lower stacks remains fixed, making the learning process very efficient. In addition, taking the advantages of BLS that can accumulate and reuse the learned knowledge, applications of BLS, Federated Broad Learning, in an open environment will be discussed. Federated Broad Learning supports learning from streaming data continuously, so it can adapt to the environment changes and provide better real-time performance.

Bio:    C. L. Philip Chen (F’07) is the Chair Professor and Dean of the College of Computer Science and Engineering, South China University of Technology and was a Chair Professor of the Faculty of Science and Technology, University of Macau, where he was the former Dean (2010-2017), after he left a professorship position in the USA for 23 years. He is a Fellow of IEEE, AAAS, IAPR, CAA, and HKIE; a member of Academia Europaea (AE), European Academy of Sciences and Arts (EASA). He received IEEE Norbert Wiener Award in 2018 for his contribution in systems and cybernetics, and machine learnings; and IEEE Joseph G. Wohl Career Award for his contributions in SMCS and IEEE in 2021. Currently, he is the Editor-in-Chief of the IEEE Trans. Cybernetics after he completed his term as the Editor-in-Chief of the IEEE Trans. Systems, Man, and Cybernetics: Systems (2014-2019). He was the IEEE SMC Society President from 2012 to 2013, an Associate Editor of the IEEE Trans. AI, SMC, Fuzzy Systems, an Associate Editor of China Sciences: Information Sciences. His current research interests include cybernetics, computational intelligence, and systems.