- Xu Z. Data Modeling: Visual Psychology Approach andL1/2Regularization Theory[M]// Proceedings of the International Congress of Mathematicians 2010 (ICM 2010):(In 4 Volumes). 2010:3151-3184.
- Xu Z, Chang X, Xu F, et al. L1/2 regularization: a thresholding representation theory and a fast solver.[J]. IEEE Transactions on Neural Networks & Learning Systems, 2012, 23(7):1013-1027.
- Xu Z B, Roach G F. Characteristic inequalities of uniformly convex and uniformly smooth Banach spaces[J]. Journal of Mathematical Analysis & Applications, 1991, 157(1):189-210.
- Xu Z B, Qiao H, Peng J, et al. A comparative study of two modeling approaches in neural networks.[J]. Neural Networks, 2004, 17(1):73-85.
- Xu Z B, Zhang R, Jing W F. When does online BP training converge?[J]. IEEE Transactions on Neural Networks, 2009, 20(10):1529-39.
- Xu Z, Sun J. Image Inpainting by Patch Propagation Using Patch Sparsity[J]. IEEE Transactions on Image Processing, 2010, 19(5):1153-1165.
- Leung Y, Zhang J S, Xu Z B. Clustering by scale-space filtering[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 22(12):1396-1410.
- Leung K S, Duan Q H, Xu Z B, et al. A new model of simulated evolutionary computation-convergence analysis and specifications[J]. Evolutionary Computation IEEE Transactions on, 2001, 5(1):3-16.
- Leung Y, Gao Y, Xu Z B. Degree of population diversity - a perspective on premature convergence in genetic algorithms and its Markov chain analysis[M]. IEEE Press, 1997.
- Qiao H, Peng J, Xu Z B. Nonlinear measures: a new approach to exponential stability analysis for Hopfield-type neural networks.[J]. IEEE Trans Neural Netw, 2001, 12(2):360-370.
| Upon the invitation of Prof. Zongben Xu, the delegate from RIKEN headed by Prof. Shun-ichi Amari visited the Institute of Information and System Sciences from April 11-15, 2011. And the XJTU-RIKEN Joint Workshop on Information Processing was held at Nanyang Hotel.|
|Machine Learning Research Group|
Mainly focus on some fundamental problems in machine learning and computer vision, especially including: self-paced learning, noise/loss modeling and tensor sparsity.
Big Data Software and Hardware Platform Research Group
Our research team focuses on the distributed systems and platforms for big data acquisition, management，and processing, including system architecture, resource management and scheduling, and distributed computing and networking. Specifically, we are focusing on the joint optimization of big data systems and analytical algorithms, algorithms for text stream processing and analysis, and big data acquisition and processing with the edge and fog architecture.
Deep Learning and Image Processing Research Group
This group focuses on the following two research directions. (1) Model-driven deep learning approach, that combines the metrits of mathematical modeling of physical mechanism and data-driven deep learning approach. (2) The fundametal algorithms in medical image anlaysis, including image reconstruction (MRI, CT, etc.), lesions detection, and multi-model image registration, etc.
Big Data and Artificial Intelligence Group