Project Description
姓名：胡晓林
职称：副教授
入职时间: 2009年
电子邮件：xlhu@tsinghua.edu.cn
电话：010-62795869
传真：010-62782266
个人主页：http://www.xlhu.cn/
教育背景
工学学士（车辆工程）, 武汉理工大学, 中国, 2001;
工学硕士（车辆工程）, 武汉理工大学, 中国, 2004;
工学博士（自动化与计算机辅助工程）, 香港中文大学, 中国, 2007.
研究领域
人工神经网络;
计算神经科学.
研究课题
国家自然科学基金(面上课题)：基于稀疏编码模型的深层学习神经网络(2013-2016)
国家自然科学基金（青年课题）：基于KKT条件的优化递归神经网络簇设计 (2009-2011);
中国博士后科学基金面上资助（一等）：一类变连接优化递归神经网络的理论与应用 (2008-2009)；
中国博士后科学基金特别资助：一类变连接优化递归神经网络及相关的高斯吸引子网络(2008-2009);
研究概况
我的主要方向是人工神经网络，重点关注递归神经网络求解优化问题及相关问题的能力，包括设计新的递归神经网络或者挖掘已有网络的一些新特点。通过对几个代表该领域当前发展水平的高效模型进行归纳总结，我们提出了一个统一的神经网络设计方法，其主要思想是不改变已有神经网络的子模块，而改变各子模块之间的连接关系，得到与原网络性能相当或比原网络性能更好的一系列新模型。利用这个框架，可对每种问题系统地设计出多个模型。此成果的意义在于：一方面，统一了该领域几个知名流派的网络模型，另一方面，大大加快了此类递归神经网络的设计速度。
近年来我开始关注计算神经科学，重点关注认知神经科学对计算机科学的启发。我们试图阐明视觉皮层的层次化结构与深度学习的关系，借鉴视觉信息处理机制的显著性检测，半监督学习的神经科学机制等。同时，我们也通过fMRI实验探索听觉认知的一些机理。
管理与服务
Associate Editor of IEEE Transactions on Neural Networks and Learning Systems
Guest Editor of the special issue of ISNN2011 in Neural Computing and Applications
ISNN 2009: 出版主席（Publication Chair）
ISNN 2010: 宣传主席 （Publicity Chair）
IWACI 2010: 宣传主席 （Publicity Chair）
ICICIP 2010: 宣传主席 （Publicity Chair）
IEEE SMC 2012：程序委员 (Program committee member)
IEEE SMC 2013：程序委员 (Program committee member)
ICACI 2013: 程序委员 (Program committee member)
奖励与荣誉
2012: 教育部自然科学奖一等奖 (第3完成人)
2009: 清华大学优秀博士后
代表性论著
[1] 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.
[2] X. Hu, P. Qi, B. Zhang, “Hierarchical K-means algorithm for modeling visual area V2 neurons,” Proc. 19th International Conference on Neural Information Processing (ICONIP), Doha, Qatar, Nov. 12-15, 2012. LNCS 7665, pp. 373–381, 2012. (Best paper award)
[3] X. Hu, C. Sun, and B. Zhang. Design of recurrent neural networks for solving constrained least absolute deviation problems. IEEE Transactions on Neural Networks (Regular Papers), vol. 21, no. 7, pp. 1073-1086, July 2010.
[4] 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, May 2010.
[5] 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.
[6] 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 (Regular Papers), vol. 20, no. 4, pp. 654–664, April 2009.
[7] X. Hu and J. Wang. An improved dual neural network for solving a class of quadratic programming problems and its k-winners-take-all application. IEEE Transactions on Neural Networks (Regular Papers), vol. 19, no. 12, pp. 2022–2031, Dec. 2008.
[8] X. Hu and J. Wang. Design of general projection neural networks for solving monotone linear variational inequalities and linear and quadratic optimization problems. IEEE Transactions on Systems, Man and Cybernetics – Part B, vol. 37, no. 5, pp. 1414-1421, 2007.
[9] X. Hu and J. Wang. Solving generally constrained generalized linear variational inequalities using the general projection neural networks. IEEE Transactions on Neural Networks (Regular Papers), vol. 18, no. 6, pp. 1697-1708, 2007.
[10] X. Hu and J. Wang. A recurrent neural network for solving a class of general variational inequalities. IEEE Transactions on Systems, Man and Cybernetics – Part B (Regular Papers), vol. 37, no. 3, pp. 528-539, 2007.
[11] X. Hu and J. Wang. Solving pseudomonotone variational inequalities and pseudoconvex optimization problems using the projection neural network. IEEE Transactions on Neural Networks (Regular Papers), vol. 17, no. 6, pp. 1487-1499, 2006.