时间：2015年9月7日（周一）上午10：00
地点：仓山校区物光大楼4楼学术报告厅
主讲：台湾元智大学电机通讯学院 林志民院长
主办：光电与信息工程学院
专家简介：Prof. Chih-Min Lin is currently a Chair Professor and Dean of Electrical and Communication Engineering College, Yuan Ze University, Taiwan. He also serves as an Associate Editor of IEEE Trans. on Cybernetics; IEEE Trans. on Fuzzy Systems; Asian Journal of Control; International Journal of Fuzzy Systems; and International Journal of Machine Learning and Cybernetics. He has been the Chair of IEEE Computational Intelligence Society Taipei Chapter, the Chair of IEEE Systems, Man, and Cybernetics Society Taipei Chapter, a Board of Governor of IEEE Taipei Session, a Board of Governor of IEEE Systems, Man, and Cybernetics Society. He has been awarded as the Distinguished Research Professor from Ministry of Science and Technology (National Science Council) three times in Taiwan, the Distinguished Engineering Professor from China Engineering Society in Taiwan, and the Distinguished Electrical Engineering Professor from Chinese Electrical Engineering Society in Taiwan. He has been invited to give 11 keynote speeches in the international conferences. He is now the Vice President of Chinese Automatic Control Society in Taiwan. His research interests include fuzzy systems, neural network, cerebellar model neural network, and intelligent control systems. He is an IEEE Fellow and IET Fellow. Till now he has published 164 journal papers and 165 conference papers.
报告摘要：Based on biological prototype of human brain and improved understanding of the functionality of the neurons and the pattern of their interconnections in the brain, a theoretical model used to explain the information-processing characteristics of the cerebellum was developed independently by Marr (1969) and Albus (1971). Cerebellar model neural network (CMNN) or called as cerebellar model articulation controller (CMAC) was first proposed by Albus in 1974. CMNN is a learning structure that imitates the organization and functionality of the cerebellum of the human brain. That model revealed the structure and functionality of the various cells and fibers in the cerebellum. The core of CMNN is an associative memory which has the ability to approach complex nonlinear functions. CMNN takes advantage of the input-redundancy by using distributed storage and can learn nonlinear functions extremely quickly due to the on-line adjustment of its system parameters. CMNN is classified as a non-fully connected perceptron-like associative memory network with overlapping receptive-fields. It has good generalization capability and fast learning property and is suitable for a lot of applications. This speech will introduce several new CMNN-based adaptive learning systems proposed by me; these systems combine the advantages of CMNN identification, adaptive learning, control technique, signal processing and image classification. In these systems, the on-line parameter training methodologies, using the Lyapunov theorem, are proposed to guarantee the stability and convergence of these systems. Moreover, the applications of these systems in nonlinear systems control, biped robot control, signal processing of communication system, and computer-aided diagnosis of breast nodules are demonstrated.