职称：教授
职务：教师
所在部门：信息科学系
个人主页

1372E 60609 jwma at math dot pku dot edu dot cn


教育经历
1992 南开大学 博士
1983 陕西师范大学 学士


工作经历
2001.9-北京大学数学科学学院教授
2011.9-2012.2美国休斯顿卫理公会医院研究所系统医学与生物工程系科学家
2005.9-2006.8日本理化学研究所脑科学研究所研究科学家
2000.7-2000.12香港中文大学计算机科学与工程系研究员
1992.7-2001.8汕头大学数学系教职员

代表作
1. Jinwen Ma, Simplex memory neural networks, Neural Networks, vol.10, no.1, pp: 25-29, 1997.201.pdf

2. Jinwen Ma, The stability of the generalized Hopfield networks in randomly asynchronous mode, Neural Networks, vol.10, no.6, pp: 1109-1116, 1997.951.pdf

3. Jinwen Ma, The object perceptron learning algorithm on generalised Hopfield networks for associative memory, Neural Computing & Applications, vol.8, no.1, pp: 25-32, 1999.536.pdf

4. Jinwen Ma, The asymptotic memory capacity of the generalized Hopfield networks，Neural Networks, vol.12, no.9, pp: 1207-1212, 1999.702.pdf

5. Jinwen Ma, Lei Xu and Michael I. Jordan, Asymptotic convergence rate of the EM algorithm for Gaussian mixtures, Neural Computation，vol.12, no.12, pp:2881-2907, 2000.844.pdf

6. Jinwen Ma, A neural network approach to real-time pattern recognition, International Journal of Pattern Recognition and Artificial Intelligence, vol.15, no.6, pp: 937-947, 2001.023.pdf

7. Jinwen Ma, A hybrid neural network of addressable and content-addressable memory, International Journal of Neural Systems, vol.13, no.3, pp: 205-213, 2003.212.pdf

8. Jinwen Ma and Taijun Wang, Entropy penalized automated model selection on Gaussian mixture, International Journal of Pattern Recognition and Artificial Intelligence, vol.18, no.8, pp: 1501-1512, 2004.329.pdf

9. Jinwen Ma, The capacity of time-delay recurrent neural network for storing spatio-temporal sequences, Neurocomputing, vol.62, pp: 19-27, 2004.450.pdf

10. Jinwen Ma, Taijun Wang, and Lei Xu, A gradient BYY harmony learning rule on Gaussian mixture with automated model selection, Neurocomputing, vol.56, pp: 481-487, 2004.641.pdf

11. Jinwen Ma and Lei Xu, Asymptotic convergence properties of the EM algorithm with respect to the overlap in the mixture, Neurocomputing，vol.68, pp: 105-129, 2005.243.pdf

12. Jinwen Ma, Bin Gao, Yang Wang, Qiansheng Cheng, Conjugate and natural gradient rules for BYY harmony learning on Gaussian mixture with automated model selection, International Journal of Pattern Recognition and Artificial Intelligence, vol.19, no.5, pp: 701-713, 2005.424.pdf

13. Jinwen Ma, Fuhai Li, Jianfeng Liu, Non-parametric statistical tests for informative gene selection, Lecture Notes in Computer Science, vol.3498, pp: 697-702, 2005.558.pdf

14. Jinwen Ma, Zhiyong Liu and Lei Xu, A further result on the ICA one-bit-matching conjecture, Neural Computation, vol.17, no.2, pp: 331-334, 2005.658.pdf

15. Jinwen Ma and Shunqun Fu, On the correct convergence of the EM algorithm for Gaussian mixtures, Pattern Recognition，vol.38, no.12, pp: 2602-2611, 2005.814.pdf

15. Jinwen Ma and Taijun Wang, A cost function approach to rival penalized Competitive learning (RPCL), IEEE Transactions on Systems, Man and Cybernetics, Part B: Cybernetics, vol.36, no.4, pp: 722-737, 2006.920.pdf

16. Jinwen Ma and Bin Cao, The Mahalanobis distance based rival penalized competitive learning algorithm, Lecture Notes in Computer Science，vol.3971, pp: 442-447, 2006.920.pdf

17. Jinwen Ma and Le Wang, BYY harmony learning on finite mixture: adaptive gradient implementation and a floating RPCL mechanism, Neural Processing Letters, vol.24, no.1, pp: 19-40, 2006.053.pdf

18. Jinwen Ma and Jianfeng Liu, The BYY annealing learning algorithm for Gaussian mixture with automated model selection, Pattern Recognition, vol.40, pp:2029-2037, 2007.206.pdf

19. Jinwen Ma, Automated model selection (AMS) on finite mixture: a new perspective for data modeling, Chinese Journal of Engineering Mathematics, vol.24, no.4, pp: 571-584, 2007.314.pdf

20. Jinwen Ma and Lei Li, Automatic straight line detection through fixed-point BYY harmony learning, Lecture Notes in Computer Sciences, vol.5226, pp: 569-576, 2008.453.pdf

21. Jinwen Ma and Xuefeng He, A fast fixed-point BYY harmony learning algorithm on Gaussian mixture with automated model selection, Pattern Recognition Letters, vol.29,no.6, pp: 701-711, 2008.538.pdf

22. Jinwen Ma, Jianfeng Liu and Zhijie Ren, Parameter estimation of Poisson mixture with automated model selection through BYY harmony learning, Pattern Recognition, vol.42, pp: 2659-2670, 2009.405.pdf

23. Fei Ge and Jinwen Ma, Spurious solution of the maximum likelihood approach to ICA, IEEE Signal Processing Letters, vol.17.no.7, pp: 655-658, 2010.332.pdf

24. Yan Yang and Jinwen Ma, Asymptotic convergence properties of the EM algorithm for mixture of experts, Neural Computation, vol.23, no.8, pp: 2140-2168, 2011.718.pdf

25. Yongsheng Dong and Jinwen Ma, Bayesian texture classification based on contourlet transform and BYY harmony learning of Poisson mixtures, IEEE Trans. on Image Processing, vol.21,no.3, pp: 901-918, 2012.732.pdf

科研项目
2012.12-2016.7数字图像中自动目标检测算法及其应用外协研究项目（负责人）

2012.1-2015.12基于数据学习的高斯过程混合体的模型选择及其应用研究国家自然科学基金(负责人)

2011.1-2014.12地震属性提取与分析国家科技重大专项子项(负责人)

2011.1-2013.12基于BYY和谐学习的RBF网络及其在非线性时间序列预测中的应用教育部博士点基金(负责人)

2009.1-2011.12统计学习算法在地震勘探中的应用外协研究项目（负责人）

2008.1-2010.12ICA并行分离算法中模板密度函数的自适应匹配与无假解分析教育部博士点基金(负责人)

2008.1-2010.12有限混合体数据的动态模型选择算法及其应用国家自然科学基金(负责人)

2007.1-2009.12独立分量分析中一比特匹配猜想及其相关学习算法研究教育部留学回国人员科研启动基金

2005.1-2007.12有限混合体数据的自动模型选择理论与应用研究国家自然科学基金(负责人)

2001.1-2003.12类别数确定及其聚类的学习理论与算法研究国家自然科学基金(负责人)

1998.1-2000.12竞争学习神经网络的正确分类问题研究广东省自然科学基金(负责人)

1998.1-2000.12时间联想的理论与应用研究国家自然科学基金(负责人)

1993.7-1996.6时空神经网络的建模、数理分析及自组织学习算法国家数学天元基金(负责人)

主讲课程
春季信息科学基础本科生/研究生

秋季人工神经网络研究生/本科生

秋季智能计算研究生/本科生

社会兼职
Mathematical Computation 主编

The Scientific World Journal 编委

2012.09-2016.08中国工业与应用数学学会理事

2001.11-2013.10《信号处理》杂志编委

2001.11-2013.10中国电子学会信号处理分会委员

荣誉获奖
2016.6《中国科技论文在线精品论文》2015年度优秀论文奖（合作者程再兴、刘双龙）

2015.9北京大学第二届产学研合作先进个人奖

2012.7北京大学优秀博士学位论文指导教师

2011.12中国人民解放军总装备部军队科技进步叁等奖

2010.10IEEE 促进国际交流奖（基于对ICSP的贡献）

2009.8第14届全国信号处理学术会议优秀论文奖(合作者何学锋)

2009.11北京大学2009年度正大奖教金(优秀奖)

2007.8第13届全国信号处理学术会议优秀论文奖(合作者徐斌)

2003.11周培源数学奖教金