Recurrent Neural Networks

I have worked for about two years on recurrent neural networks with Prof. Jun Wang at the Chinese University of Hong Kong. The study is mainly on the dynamical behavior of the recurrent neural networks, and how the dynamical behavior may help to solve some engineering optimization problems.

My research interests have shifted to the study of visual perception and inference since then.

Publications:

• Shubao Liu and Jun Wang, A Simplified Dual Neural Network for Quadratic Programming with Application for K-Winners-Take-All Operation, IEEE Transactions on Neural Networks (TNN), vol. 17, no. 6, pp. 1500-1510, 2006.
• Shubao Liu and Jun Wang, Obstacle Avoidance for Kinematically Redundant Manipulators Using the Deterministic Annealing Neural Network, International Symposium on Neural Networks, May 2005.
• Shubao Liu and Jun Wang, A New K-Winners-Take-All Neural Network, International Joint Conference on Neural Networks, 2005.
• Shubao Liu and Jun Wang, A Dual Neural Network for Bi-Criteria Torque Optimization of Redundant Robot Manipualtors, Proceedings of International Conference on Neural Information Processing, LNCS vol. 3316, pp. 1142-1147, Springer-Verlag, Berlin, Germany, November 2004.
• Shubao Liu and Jun Wang, Blind Adaptive Multiuser Detection Using a Recurrent Neural Network, Proceedings of International Conference on Communications, Circuits and Systems, pp. 1071-1075, June 2004.