馬盡文

馬盡文，北京大學數學科學學院教授、博士生導師。

基本介紹

• 中文名：馬盡文
• 國籍：中國
• 職業：教授 博士生導師
• 畢業院校：南開大學
• 學位/學歷：理學博士
• 職務：北京大學數學科學學院信息科學系主任

學習與工作經歷

1992年南開大學機率論與數理統計專業博士畢業。

1992年到汕頭大學數學系、數學研究所工作。

1999年套用數學專業教授。

2001年9月調入北京大學數學科學學院信息科學系工作，現為套用數學專業教授、博士生導師、系主任。

從1995年至2004年，多次到香港中文大學計算機科學與工程學系進行合作研究，擔任副研究員(ResearchAssociate)或研究員(ResearchFellow)。

2005年9月至2006年8月在日本理化學研究所(RIKEN)腦科學研究所Amari研究組進行科學研究，擔任研究科學家(ResearchScientist)。

2011年9月至2012年3月在美國休斯頓衛理會醫院系統科研中心繫統醫學和生物工程系進行科學研究，擔任科學家(Scientist)。

研究方向

神經計算，獨立分量分析(ICA)，統計學習理論與算法，智慧型信息處理和生物信息學。

科研成就

從上世紀九十年代初開始從事人工神經網路和學習算法方面的理論及其套用研究，現在主要針對大數據的挑戰進行數據挖掘、機器學習和智慧型信息處理等方面的研究。目前已發表學術論文100餘篇，其中被SCI收錄50餘篇，被引用1000餘次，多篇論文發表在《NeuralComputation》、《IEEETrans.onSMC-B》、《IEEETrans.onImageProcessing》、《NeuralNetworks》、《PatternRecognition》等國際著名期刊和SIGIR、SIGKDD等國際重要學術會議文集上。在高斯混合模型的參數學習和自適應模型選擇方面建立了一套系統的理論與有效的學習算法,並被廣泛地套用於聚類分析、模型識別和圖像處理的等領域。先後主持國家自然科學基金項目6項、國家科技重大專項子項1項和省部級及橫行科研基金項目8項。

曾被邀請到美國、英國、加拿大、澳大利亞、日本、台灣和香港等國家和地區參加國際學術會議和進行學術交流20餘次，交流學術論文30餘篇。6次被國內外學術會議邀請做特邀報告。

榮譽頭銜

現擔任中國工業與套用數學學會理事，中國電子學會信號處理分會委員，《TheScientificWorldJournal》、《JournalofIndustrialMathematics》、《信號處理》等雜誌的編委、《數學計算》雜誌的主編。曾多次擔任ISNN,ICIC,ICONIP,ICSP等重要國際學術會議的程式委員會議委員。並擔任1999年中國神經網路和信號處理學術會議的程式委員會主席。

主要論文

1. 自適應模型選擇與聚類分析(Adaptive Model Selection and Clustering Analysis)

[1.1] Hongyan Wang and Jinwen Ma, Simultaneous model selection and feature selection via BYY harmony learning, Lecture Notes in Computer Science, vol.6676, pp: 47-56, 2011.

[1.2] Yanqiao Zhu and Jinwen Ma, A stage by stage pruning algorithms for detecting the number of clusters in a dataset, Lecture Notes in Computer Science, vol. 6215, pp: 222-229, 2010.

[1.3] 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.

[1.4] Chonglun Fang and Jinwen Ma, A novel k’-means algorithm for clustering analysis, Proceedings of the 2 International Conference on Biomedical Engineering and Informatics (BMEI, 2009), 17-19 October 2009, Tianjin,China.

[1.5] Lin Wang and Jinwen Ma, A kurtosis and skewness based criterion for model selection on Gaussian mixture, Proceedings of the 2 International Conference on Biomedical Engineering and Informatics (BMEI, 2009), 17-19 October 2009, Tianjin, China.

[1.6] Jinwen Ma and Xuefen He, A fast fixed-point BYY harmony learning algorithm on Gaussian mixture with automated model selection, Pattern Recognition Letters, vol.29, pp: 701-711, 2008.

[1.7] Lei Li and Jinwen Ma, A BYY scale-incremental EM algorithm for Gaussian mixture learning, Applied Mathematics and Computation, vol.205, pp: 832-840, 2008.

[1.8] Hengyu Wang, Lei Li and Jinwen Ma, The competitive EM algorithm for Gaussian mixtures with BYY harmony criterion, Lecture Notes in Computer Science, vol.5226, pp: 552-560, 2008.

[1.10] Lei Li and Jinwen Ma, A BYY split-and-merge EM algorithm for Gaussian mixture learning, Lecture Notes in Computer Science, vol.5263, pp: 600-609, 2008.

[1.11] Zhijie Ren, Jinwen Ma, BYY Harmony Learning on Weibull Mixture with Automated Model Selection, Lecture Notes in Computer Science, vol.5263, pp: 589-599, 2008.

[1.12] Hongyan Wang and Jinwen Ma, BYY harmony enforcing regularization for Gaussian mixture learning, Proceedings of the 9 International Conference on Signal Processing (ICSP, 2008, 26-29 Oct., Beijing,China), pp: 1664-1667.

[1.13] 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.

[1.14] Kai Huang, Le Wang, and Jinwen Ma, Efficient training of RBF networks via the BYY automated model selection learning algorithms, , Lecture Notes in Computer Science， vol.4491, pp: 1183-1192，2007.

[1.15] Jinwen Ma, Automated model selection (AMS) on finite mixtures: a theoretical analysis, Proceedings of 2006 International Joint Conference on Neural Networks (IJCNN’06), pp: 8255-8261, 2006.

[1.16] 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.

[1.17] 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.

[1.18] 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.

[1.19] Jinwen Ma and Qicai He, A dynamic merge-or-split learning algorithm on Gaussian mixture for automated model selection, Lecture Notes in Computer Science， vol.3578, pp: 203-210, 2005.

[1.20] Jinwen Ma, Bin Gao, Yang Wang, and 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.

[1.21] 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.

[1.22] 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.

[1.23] Hua-Jun Zeng, Qi-Cai He, Zheng Chen, Wei-Ying Ma, and Jinwen Ma, Learning to cluster web search results, Proceedings of the 27th International ACM Conference on Research and Development in Information Retrieval (SIGIR’04), Sheffield, UK, July 25-29, 2004,pp: 210-217.

2. 圖像分析與紋理分類(Image Analysis and Texture Classification)

[2.1] Chonglun Fang and Jinwen Ma, A fixed-point EM algorithm for straight line detection, Lecture Notes in Computer Science, vol.6676,pp:136-143,2011.

[2.2] Yongsheng Dong and Jinwen Ma, Contourlet-based texture classification with product Bernoulli distributions, Lecture Notes in Computer Science, vol.6676,pp:9-18,2011.

[2.3] Yongsheng Dong and Jinwen Ma, Wavelet-based image texture classification using local energy histograms, IEEE Signal Processing Letters, vol.18.no.4, pp: 247-250, 2011.

[2.4] Jinwen Ma and Lei Li, Automatic straight line detection through fixed-point BYY harmony learning, Lecture Notes in Computer Science, vol.5226, pp: 569-576, 2008.

[2.5] Gang Chen, Lei Li, Jinwen Ma, A gradient BYY harmony learning algorithm for straight line detection, Lecture Notes in Computer Science, vol.5263, pp: 618-626, 2008.

[2.6] Zhiwu Lu, Qiansheng Cheng, Jinwen Ma, A gradient BYY harmony learning algorithm on mixture of experts for curve detection, Lecture Notes in Computer Science， vol.3578, pp: 250-257，2005.

3. 獨立分量分析(Independent Component Analysis）

[3.1] Fei Ge and Jinwen Ma, An efficient pairwise kurtosis optimization algorithm for independent component analysis, Communications in Computer and Information Science, vol.93, pp:94-101, 2010.

[3.2] 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.

[3.3] Fei Ge and Jinwen Ma, Analysis of the Kurtosis-sum objective function for ICA, Lecture Notes in Computer Science, vol.5263, pp: 579-588,2008.

[3.4] Zhe Chen and Jinwen Ma, Contrast functions for non-circular and circular sources separation in complex-valued ICA, Proceedings of 2006 IEEE International Joint Conference on Neural Networks (IJCNN’06), pp: 1192-1199, 2006.

[3.5] Jinwen Ma , Zhe Chen and Shun-ichi Amari, Analysis of feasible solutions of the ICA problem under the one-bit-matching condition, Lecture Notes in Computer Science，vol.3889, pp: 838-845, 2006.

[3.6] Jinwen Ma, Dengpan Gao, Fei Ge and Shun-ichi Amari, A one-bit-matching learning algorithm for independent component analysis, Lecture Notes in Computer Science，vol.3889, pp: 173-180, 2006.

[3.7] Jinwen Ma, Fei Ge and Dengpan Gao, Two adaptive matching learning algorithms for independent component analysis, Lecture Notes in Artificial Intelligence, vol.3801, pp: 915-920, 2005.

[3.8] Dengpan Gao, Jinwen Ma and Qiansheng Cheng, An alternative switching criterion for independent component analysis (ICA), Neurocomputing， vol.68, pp: 267-272, 2005.

[3.9] 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.

4. 生物信息學 (Bioinformatics)

[4.1] Wei Wang and Jinwen Ma, Density Based merging search of functional modules in protein-protein interaction (PPI) networks, Lecture Notes in Computer Science, vol. 6215, pp: 634-649, 2010.

[4.2] Fuhai Li, X Zhou, J Ma, and STC Wong, Multiple nuclei tracking using integer programming for quantitative cancer cell cycle analysis, IEEE Transactions on Medical Imaging, vol.29, no.1, pp: 95-105, 2010.

[4.3] Wei Xiong, Zhibin Cai, and Jinwen Ma, A DSRPCL-SVM approach to informative gene analysis, Genomics, Proteomics & Bioinformatics, vol.6, no.2, pp: 83-90, 2008.

[4.4] Fuhai Li, Xiaobo Zhou, Jinmin Zhu, Wieming Xia, Jinwen Ma and Stephen T. C. Wong, Workflow and methods of high-content time-lapse analysis for quantifying intracellular calcium signals, Neuroinformatics, vol. 6, no.2, pp: 97-108, 2008.

[4.5] Fuhai Li，XiaoboZhou， Jinmin Zhu，Jinwen Ma，XudongHuangm and Stephen TC Wong, High content image analysis for human H4 neuroglioma cells exposed to CuO nanoparticles, BMC Biotechnology , 2007, 7: 66.

[4.6] F. Li, X. Zhou, J. Ma, & Stephen T. C. Wong, An automated feedback system with the hybrid model of scoring and classification for solving over-segmentation problems in RNAi high content screening, Journal of Microscopy, Vol.226, pt 2, pp: 121-132, 2007.

[4.7] Liangliang Wang and Jinwen Ma, Informative gene set selection via distance sensitive rival penalized competitive learning and redundancy analysis, Lecture Notes in Computer Science，vol.4491, pp: 1227-1236, 2007.

[4.8] Liangliang Wang and Jinwen Ma, A post-filtering gene selection algorithm based on redundancy and multi-gene analysis, International Journal of Information Technology, vol.11, no.8, pp: 36-44, 2005.

[4.9] Jinwen Ma, Minghua Deng, Application of DNA microarray data to medicine, Physics (in Chinese), vol.34, no.5, pp: 371-380, 2005.

[4.10] Jinwen Ma, Fuhai Li, and Jianfeng Liu, Non-parametric statistical tests for informative gene selection, Lecture Notes in Computer Science，vol.3498, pp: 697-702, 2005.

[4.11] Jun Luo and Jinwen Ma, A multi-population X-2 test approach to informative gene selection, Lecture Notes in Computer Science，vol. 3578, pp: 406-413, 2005.

[4.12] Fei Ge and Jinwen Ma, An information criterion for informative gene selection, Lecture Notes in Computer Science，vol.3498, pp: 703-708, 2005.

[4.13] Lin Deng, Jinwen Ma, and Jian Pei, Rank sum method for related gene selection and its application to tumor diagnosis, Chinese Science Bulletin, vol.49, no.15, pp: 1652-1657, 2004.

[4.14] Lin Deng, Jian Pei, Jinwen Ma, and Dik Lun Lee, A rank sum test method for informative gene discovery, Proceedings of the Tenth ACM International Conference on Knowledge Discovery and Data Mining (SIGKDD’04), Seattle, Washington, USA, August 22-25, 2004, pp: 410-419.

5. EM算法 (EM Algorithm)

[5.1] Yan Yang and Jinwen Ma, Asymptotic convergence properties of the EM algorithm for mixture of experts, Neural Computation, In Press, 2011.

[5.2] Yan Yang and Jinwen Ma, An efficient EM approach to parameter learning of the mixture of Gaussian processes, Lecture Notes in Computer Science，vol. 6676, pp: 165-174, 2009.

[5.3] Yan Yang and Jinwen Ma, A single loop EM algorithm for the mixture of experts architecture, Lecture Notes in Computer Science，vol. 5552, pp: 959-968, 2009.

[5.4] 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.

[5.5] 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.

[5.6] 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.

6. 聯想記憶與時空序列(Associative Memory and Spatio-temporal Sequence)

[6.1] Fuhai Li, Jinwen Ma, and Dezhi Huang, MFCC and SVM based recognition of Chinese vowels, Lecture Notes in Artificial Intelligence, vol.3802, pp: 812-819, 2005.

[6.2] Jinwen Ma, The capacity of time-delay recurrent neural network for storing spatio-temporal sequences, Neurocomputing, vol.62, pp: 19-27, 2004.

[6.3] Jianwei Wu, Jinwen Ma, and Qiansheng Cheng, Further results on the asymptotic memory capacity of the generalized Hopfield network, Neural Processing Letters, vol.20, pp: 23-38, 2004.

[6.4] 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.

[6.5] Jinwen Ma and Dezhi Huang, A neural network filter for complex spatio-temporal patterns, Proceedings of the International Joint Conference on Neural Networks (IJCNN’02), Hawaii, USA, May 12-17 2002, vol.1, pp: 1028-1033.

[6.6] 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.

[6.7] Jinwen Ma, The asymptotic memory capacity of the generalized Hopfield networks，Neural Networks, vol.12, no.9, pp: 1207-1212, 1999.

[6.8] 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.

[6.9] Jinwen Ma, The stability of the generalized Hopfield networks in randomly asynchronous mode, Neural Networks, vol.10, no.6, pp: 1109-1116, 1997.

[6.10] Jinwen Ma, Simplex memory neural networks, Neural Networks, vol.10, no.1, pp: 25-29, 1997.