17th IEEE International Conference on Networking, Sensing and Control

 October 30 - November 2,  2020, Nanjing, China


Doctor JunzoWatada, Professor Emeritus

Waseda University, Japan


        We have worked on artificial neural network (ANN) from 1990. The most shocking was that many researchers left from NN in 1970s because of the NN structural problem. We employed various NN to solve problems. We built double layered neural networks in 1990s to solve mean-variance problems, that is, quadratic programming problems such as portfolio problems in financial engineering. The double layered neural networks consist of Hopfield machine and Boltzmann machine. The two neural networks collaborate to solve the quadratic mean-variance problems in the way that the upper level NN selects optimal neurons and the lower level NN decided each optimal weights. But bi level programming problem is more complicated. Even bi level linear programming problem is NP-hard to solve it. We realized that several wrong optimum results were presented in journal papers. We built a hybrid recurrent neural network to solve bi-level quadratic programming in 2014. Also we apply the system to solve real applications. We explain such research directions.

       Finally we will report recent resulted of deep learning understanding of video pictures base on Masking Vision Based Autonomous Navigation.

Short Bio:

Dr. Junzo Watada received his B.Sc. and M.Sc. degrees in electrical engineering from Osaka City University, Japan, in 1970 and 1972 respectively, and his Ph.D. degree from Osaka Prefecture University, Japan. Currently, he is an invited researcher, IPS Research Center, Waseda University at Kitakyushu, Japan and a professor emeritus, Waseda University, Japan.. He received the Henri Coanda Medal Award from Inventico in Romania in 2002. He is a Life Fellow of the Japan Society for Fuzzy Theory and intelligent informatics (SOFT). Prof Watada is an IEEE life senior member, Executive Chair of ISME, WCICME, the president (2019-2021), Forum of Interdisciplinary Mathematics after being a vice-president for six years. He commits himself in editing various international journals as a principal editor of several journals and an editorial board member of more than 30 journals. His professional interests include artificial neural network, human tracking, human centric data mining, soft computing, knowledge engineering, financial engineering and management engineering.