EN 中文

 

Zhang, Bo

Date：2019-09-30
Professor, Department of Computer Science and Technology
PI，IDG/McGovern Institute, Tsinghua University
Academician of CAS
 
 

                             

[Research Interests]

Artificial Intelligence and Pattern Recognition

Research outputs of mine and the group I lead majorly fall into the following three fields:

In Artificial Intelligence, collaborating with Professor Ling Zhang, I have proposed a problem solving theory based on quotient space, which has been successfully applied to areas such as heuristic search, fuzzy analysis and reasoning, and robotic task and motion planning. Based on this theory, we have extended our research and presented several new algorithms for multi-granular computing and hierarchical problem solving, which are proven to be effective in reducing computational complexities.

In Artificial Neural Networks, we have quantitatively analyzed the behavior and characteristics of probabilistic logic neuron (PLN) networks, and presented a programming-based learning algorithm of neural networks with feedback connections and a structural learning algorithm of feed-forward neural networks. Compared with traditional search-based algorithms, our new learning algorithms not only have a solid theoretical basis, but also provide immediate support to designing the structure of neural networks.

In Machine Learning, we have investigated the structural prediction learning theory and its applications, and presented a new learning algorithm-Maximum Entropy Discrimination Markov Networks, which has been applied to tasks of mining web pages' structure, and image retrieval and classification.

[Education & Experiences]

Dr. Bo Zhang graduated from the automatic control department of Tsinghua University in 1958, and has been teaching in Tsinghua University since the same year. He was a visiting scholar at the University of Illinois from February 1980 to February 1982. In 2011, the University of Hamburg awarded honorary doctor of natural science. He used to be the deputy director of the university degree committee, and is now the technical consultant of Microsoft Research Asia.

[Selected Publications]

  • Bo Zhang and Ling Zhang, Hierarchy and statistical heuristic search, Future Generation Computer Systems (Netherlands), 6(1), pp. 43-47, 1990.
  • Bo Zhang, Ling Zhang, et al, A quantitative analysis of behaviors of the PLN network, Neural Networks, 5, pp.639-644, 1992.
  • Bo Zhang, Ling Zhang, et al, Programming based learning algorithms of neural networks with self-feedback connections, IEEE Transaction on Neural Networks, 6(3), pp.771-775, 1995.
  • Bo Zhang, Ling Zhang, et al, The complexity of learning in PLN networks, Neural Networks, 8(2), pp221-228, 1995.
  • Ling Zhang, Bo Zhang, et al, Generating and coding of fractal graphs by neural network and mathematical morphology methods, IEEE Transaction on Neural Networks, 7(2), pp.400-407, 1996.
  • Ling Zhang and Bo Zhang, A geometrical representation of McCulloch-Pitts neural model and its applications, IEEE Trans. on Neural Networks, 10(4), pp.925-929, 1999.
  • Feng Jing, Mingjing Li, Hong-Jiang Zhang, Bo Zhang, An Efficient and Effective Region-based Image Retrieval Framework, IEEE Transaction on Image Processing, vol.13, no.5,, pp.699-709, May 2004.
  • Feng Jing, Mingjing Li, Hong-Jiang Zhang, Bo Zhang, A Unified Framework for Image Retrieval Using Keyword and Visual Features, IEEE Transaction on Image Processing, Vol. 14, No. 7 , pp. 979-989, 2005.
  • L. Zhang and Bo Zhang, Fuzzy Reasoning Model under Quotient Space Structure, Information Sciences, vol.173, issue 4, pp.353-364, June 2005.
  • L. Zhang and Bo Zhang, The structure analysis of fuzzy sets, International Journal of Approximate Reasoning, 40, pp. 92-108, 2005.
  • Jun Zhu, Zaiqing Nie, Bo Zhang, and Ji-Rong Wen. Dynamic Hierarchical Markov Random Fields and their Application to Web Data Extraction. The 24th International Conference on Machine Learning (ICML), Corvalis, Oregon, USA, June 20-24, 2007.
  • Jun Zhu, Zaiqing Nie, Bo Zhang, Ji-Rong Wen, Dynamic Hierarchical Markov Random Fields for Integrated Web Data Extraction, Journal of Machine Learning Research, vol. 9, pp.1583-1614, 2008.
  • Jun Zhu, Eric P. Xing, and Bo Zhang. Laplace Maximum Margin Markov Networks. The 25th International Conference on Machine Learning (ICML), Helsinki, Finland, July 5-9, 2008.
  • Ling Zhang, Bo Zhang, The theory and application of tolerance relations, International Journal of Granular Computing, Rough Sets and Intelligent Systems, Vol.1, No. 2, pp.179 -189, 2009.
  • Bo Zhang and Ling Zhang, Theory and Applications of Problem Solving, Elsevier Science Publishers B. V., North-Holland-Amsterdam, London, New York, Tokyo, 1992.