[ICNSC 2020 Front Matter]

2020 2020 IEEE International Conference on Networking, Sensing and Control (ICNSC)  
We have worked on artificial neural network (ANN) from 1990. Recently ANN influences us by the deep learning structure. We intend to talk about our research of ANN to solve problems. We built double-layered ANNs in 1990s to solve mean-variance problems, that is, quadratic programming problems such as portfolio problems in financial engineering. The double-layered ANNs consist of Hopfield machine and Boltzmann machine. The two kinds of ANN collaborate to solve the quadratic mean-variance
more » ... in the way that the upper level ANN selects optimal neurons and the lower level ANN 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 found that several wrong optimum results were presented in journal papers. We built a hybrid recurrent ANN 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 based on Masking Vision Based Autonomous Navigation. Speaker Biography Dr. Junzo Watada received his B.Sc. and M.
doi:10.1109/icnsc48988.2020.9311391 fatcat:e7vdat475ncofjhzmdwwpuy23y