计算机科学与技术系

Department of Computer Science and Technology

  • Xiaolin HU
  • Associate Professor
  • Department of Computer Science and Technology
  • Joined Department: 2009
  • Email:xlhu@tsinghua.edu.cn
  • URL: www.xlhu.cn
  • Phone:+86-10-62795869
  • Fax:+86-10-62782266

Education background

Bachelor of Automotive Engineering, Wuhan University of Technology, Wuhan, China, 2001;

Master of Automotive Engineering, Wuhan University of Technology, Wuhan, China, 2004;

Ph.D. in Automation and Computer-Aided Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China, 2007.

Social service

Associate Editor, IEEE Transactions on Neural Networks and Learning Systems

Areas of Research Interests/ Research Projects

Artificial Neural Networks

Computational Neuroscience

Courses

Neural and Cognitive Computation (80240642,Graduate).

Research Projects

National Natural Science Foundation of China: Design of Recurrent Neural Network Groups for Optimization based on KKT Conditions (2009-2011);

National Natural Science Foundation of China: Deep Learning Networks based on Sparse Coding Models (2013-2016)

Research Status

I'm working in the interaction between computer science and cognitive neuroscience.

On one hand, I'm interested in unraveling the secrets of the brain, especially the mechanisms of sensory information processing and decision making. Two main techniques I rely on are hierarchical computational models and Bayes theory. Another technique I'm now trying to use is functional magnetic resonance imaging (fMRI) combined with machine learning methods.

On the other hand, I'm interested in brain-inspired computing methods. Currently I'm trying to integrate more neuroscience knowledge into deep learning models for boosting their performances as well as efficiency for object recognition and detection. In addition, I'm involved in a neuromorphic hardware project, which aims at developing an intelligent and energy-efficient brain-like system. My previous interest is the design of recurrent neural network for solving optimization problems, which also lies in this direction. 

Honors And Awards

Ministry of Education, The People's Republic of China: Neurodynamic Optimization: Models and Applications, Natural Science Award, 1st Class (2012);

Tsinghua University: Excellent Postdoctoral Fellow (2009);

ICONIP 2012: Best Paper Award (2012). 

Academic Achievement

[1] P. Qi, X. Hu, “Learning nonlinear statistical regularities in natural images by modeling the outer product of image intensities,” Neural Computation (accepted)

[2] X. Hu, J. Zhang, P. Qi, B. Zhang, “Modeling response properties of V2 neurons using a hierarchical K-means model,” Neurocomputing, vol. 134, pp. 198-205, 2014.

[3] X. Hu, J. Zhang, J. Li, B. Zhang, “Sparsity-regularized HMAX for visual recognition,” PLOS ONE, vol. 9, no. 1, pp. 1-12, 2014.

[4] X. Hu and J. Wang, “Solving the assignment problem using continuous-time and discrete-time improved dual networks,” IEEE Transactions on Neural Networks and Learning Systems, vol. 23, no. 5, pp. 821-827, 2012.

[5] X. Hu and B. Zhang, “A Gaussian attractor network for memory and recognition with experience-dependent Learning,” Neural Computation, vol. 22, no. 5, pp. 1333-1357, 2010.

[6] X. Hu, C. Sun and B. Zhang, “Design of recurrent neural networks for solving constrained least absolute deviation problems,” IEEE Transactions on Neural Networks, vol. 21, no. 7, pp. 1073-1086, July 2010.

[7] X. Hu and B. Zhang, “An alternative recurrent neural network for solving variational inequalities and related optimization problems,” IEEE Transactions on Systems, Man and Cybernetics - Part B, vol. 39, no. 6, pp. 1640-1645, Dec. 2009.

[8] X. Hu and B. Zhang, “A new recurrent neural network for solving convex quadratic programming problems with an application to the k-winners-take-all problem,” IEEE Transactions on Neural Networks, vol. 20, no. 4, pp. 654–664, April 2009.