王健
发布人:张锋  发布时间:2018-01-24   浏览次数:3097

 

 

★王健

男,197811月生,博士,理学院副教授,基础数学系主任,国际事务办公室主任、青岛市侨联青年委员。

联系电话:+86-13061345702

电子邮箱:  wangjiannl@upc.edu.cn

通讯地址: 青岛经济技术开发区长江西路66

邮政编码:  266580

★研究方向:

机器学习、最优化理论、神经网络

★教育经历:

2008.07--2012.07  大连理工大学,计算数学, 博士, 导师:吴微 副教授

2006.09--2008.07  大连理工大学,计算数学, 硕士, 导师:李正学 副教授

1998.09--2002.07  石油大学(华东), 计算数学及其应用软件,学士,

★工作经历:

2012.12--至今中国石油大学(华东)            副教授

2012.07--2012.12  中国石油大学(华东)            讲师

2002.07--2006.07  中国石油大学(华东)            助教

★学术经历:

2017.02--2017.03   印度统计研究所(印度)访问学者 合作导师: Nikhil R. Pal

2013.07--2014.02   路易斯维尔大学(美国)  博士后 合作导师: Jacek M.Zurada

2012.08--2015.06   大连理工大学博士后合作导师:王兢

2011.10--2012.01   西安交通大学国内访学 合作导师:徐宗本

2010.09--2011.09   路易斯维尔大学(美国)联合培养合作导师: Jacek M. Zurada

★学术兼职:

2018.01—至今 《IEEE Transactions on Neural Networks and Learning Systems》 副主编

2014.03--至今 《Journal of Applied Computer Science Methods》副主编

2009.07--至今国际电气电子工程师协会(IEEE)会员;

IEEE Transactions on Neural Networks and learning Systems, Neural Networks, Neurocomputing, International Journal of Applied Mathematics and Computer Science》,《Neural Computing and Applications》等多个杂志审稿人。

★特邀报告:

2012.04  Convergence of Cyclic and Almost-Cyclic Learning with Momentum for Feedforward Neural Networks, 哈尔滨工业大学;

2014.04  带惩罚项前馈神经网络学习算法的若干最新结果, 衡阳师范学院。

2016.07  神经网络模型设计/应用与理论分析, 山东省计算中心, 济南。

2017.06  基于 Group Lasso 惩罚项的神经网络特征选择模型设计与分析,衡阳师范学院。

★学术会议:

2009.07   第十一届全国高校计算数学年会, 贵阳,贵州;

2011.07   International Joint Conference on Neural Networks, 圣何塞,加利福尼亚州,美国

2012.07   The 9th International Symposium on Neural Networks, 沈阳, 辽宁.

2014.06   The 13rd international conference on artificial intelligence and soft computing, 扎克帕内,波兰。

2015.11   The 13rd Chinese Workshop on Machine Learning and Applications (13界中国机器学习及其应用研讨会), 南京大学, 南京,中国。

2015.12   The International Conference on Extreme Learning Machines (ELM2015),杭州,中国。

2016.01   数学与信息科学交叉前沿论坛,太原,中国。

2016.05   International Symposium on New Trends in Computational Intelligence(国际计算智能最新进展学术交流会),青岛,中国(会议执行主席)

2016.08   International Conference on Intelligent Computing, 兰州, 中国。

2016.10   The 23rd International Conference on Neural Information Processing, 京都, 日本.

2017.06   Fourteenth International Symposium on Neural Networks (ISNN 2017)14届国际神经网络研讨会, 札幌, 日本

2017.11   The 24rd International Conference on Neural Information Processing, 广州, 中国Publication Chair

★奖励/荣誉:

2011.12   “年度科技创新奖”            大连理工大学

2012.03    第四届博士生学术之星”      大连理工大学

2013.04    美国大学生数学建模竞赛二等奖(指导教师);

2014.06    入选青岛市黄岛区“智岛计划”紧缺人才;

2014.10    入选中国石油大学(华东)青年教师人才建设工程“拔尖人才工程项目;

2015.10    获中国石油大学(华东)2013-2015年度“优秀教师”荣誉称号;

2016.11    获中国石油大学(华东)“优秀班主任”荣誉称号;


★学术成果:

2012.06   Convergence of cyclic and almost-cyclic learning with momentum for feedfoward neural networks. 辽宁省自然科学学术成果奖、二等奖, 辽宁省人力资源和社会保障厅. 位次: 1/4

2013.08   Computational properties and convergence analysis of BPNN for cyclic and almost cyclic learning with penalty. 辽宁省自然科学学术成果奖、二等奖, 辽宁省人力资源和社会保障厅. 位次: 1/3


★主持项目:

          2012.10--2014.10  中国博士后科学基金面上项目(基于L1/2正则化方法的前馈神经网络收敛性分        析 No.2012M520624)      5万元;

          2013.01--2014.12  中央高校基本科研业务费专项基金(L1/2正则化方法在神经网络中的应用与分析 No. 13CX02009A      4万元;

          2013.10--2016.10  山东省自然科学基金青年项目(L1/2正则化方法在神经网络中的设计与理论研究No. ZR2013FQ004)          5万元;

           2014.01--2016.12   教育部高等学校博士学科点专项科研基金(神经网络容错学习算法设计与确定型收敛性研究No. 20130133120014)         5万元;

          2014.01--2016.12   国家自然科学基金青年项目(前馈神经网络容错学习算法的设计与确定型收敛性研究No. 61305075)      25万元;

          2015.09--2018.09  中央高校基本科研业务费专项基金-科技专项(深水钻井安全评价的超限学习机模型研究与分析No. 15CX05053A      10万元;

2016.01--2019.01   国际合作交流基金(信息计算课程全英文授课模式研究与实践)   15万元;

2017.01--2020.01   国际合作交流基金(大数据智能信息处理高端引智计划)         10万元;


★主要论著:

[1]  Jian Wang, Jie Yang, Wei Wu. Convergence of cyclic and almost-cyclic learning with momentum for feedforward neural networks, IEEE Transactions on Neural Networks, 22(8), pp.1297-1306, 2011. (SCI 一区)

[2]  Wei Wu, Jian Wang, Mingsong Cheng, Zhengxue Li. Convergence analysis of online gradient method for BP neural networks, Neural Networks, 24(1), pp. 91-98, 2011. (SCI 二区)

[3]  Jian Wang, Wei Wu, Jacek M. Zurada. Deterministic convergence of conjugate gradient method for feedforward neural networks, Neurocomputing, 74(14-15), pp. 2368-2376, 2011. (SCI 二区)

[4]  Jian Wang, Wei Wu, Zhengxue Li, Long Li. Convergence of gradient method for double parallel feedforward neural network, International Journal of Numerical Analysis and Modeling, 8(3), pp. 484-495, 2011. (SCI 三区)

[5]  Jian Wang, Wei Wu, Jacek M. Zurada. Boundedness and convergence of MPN for cyclic and almost cyclic learning with penalty, International Joint Conference on Neural Networks (IJCNN), Jul 31-Aug 5, 2011, pp. 125-132, San Jose, California, USA, 2011. (EI)

[6]  Jian Wang, Wei Wu, Jacek M. Zurada. Computational properties and convergence analysis of BPNN for cyclic and almost cyclic learning with penalty.Neural Networks, 33, pp. 127-135, 2012. (SCI 二区)

[7]  Jian Wang, Wei Wu, Jacek M. Zurada. Computational Properties of Cyclic and Almost-Cyclic learning with momentum for feedforward neural networks, International Symposium on Neural Networks (ISNN), Jul 18-21, 2012, Shenyang, Liaoning, China, 2012. (EI)

    [8]  王健,中美线性代数教学方法的对比与分析,吉林工程技术师范学院学报,28(2), pp. 74-75. 2012.

Jian Wang, The Linear Algebra Teaching Methods Comparison andAnalysis between China and America. Journal of Jilin Teachers Institute of Engineering and Technology, 28(2), pp. 74-75, 2012

[9]  Jan Chorowski, Jian Wang, Jacek M. Zurada. Review and performance comparison of SVM- and ELM-based classifiers, Neurocomputing, 128, pp. 507-516, 2014. (SCI 二区)

[10] Wei Wu, Qinwei Fan, Jacek M. Zurada, Jian Wang, Dakun Yang, Yan Liu. Batch gradient method with smoothing L1/2 regularization for training of feedforward neural networks,Neural Networks, 50, pp. 72-78, 2014. (SCI 二区)

[11]Yan Liu, Wei Wu, Qinwei Fan, Dakun Yang, Jian Wang. A modified gradient learning algorithm with smoothing L1/2 regularization for Takagi–Sugeno fuzzy models, Neurocomputing, 138, pp. 229-237, 2014. (SCI 二区)

[12] Jian Wang, Jacek M. Zurada, Yanjiang Wang, Jing Wang, Guofang Xie. Boundedness of Weight Elimination for BP Neural Networks, The 13th International Conference on Artificial Intelligence and Soft Computing (ICAISC), June 1-5, 8467, pp. 155-165, 2014, Zakopane, Poland. (EI)

[13]Yetian Fan, Wei Wu, Wenyu Yang, Qin-wei Fan,Jian Wang. A pruning algorithm with L 1/2 regularizer for extreme learning machine.Journal of Zhejiang University - Science C 15(2): 119-125 (2014) (SCI 四区)

[14] Hongmei Shao, Jian Wang, Lijun Liu, Dongpo Xu, Wendi Bao. Relaxed conditions for convergence of batch BPAP for feedforward neural networks. Neurocomputing, 153, pp. 174-179, 2015. (SCI 二区)

    [15] Bingjia Huang, Jian Wang, Yanqing Wen, Hongmei Shao, Jing Wang. Convergence analysis of inverse iterative algorithms for neural networks with L1/2 penalty.Journal of China University of Petroleum, Vol. 39, No. 2, pp. 164-170, 2015. (EI)

[16] Jian Wang, Guoling Yang, Shan Liu, Jacek M. Zurada, Convergence Analysis of Multilayer Feedforward Networks Trained with Penalty Terms, Journal of Applied Computer Science Methods, Vol. 7, No. 2, pp. 89-103, 2015.

[17] 王健, 谢国芳, 刘珊, 邵红梅, 黄炳家. 研究性教学在教学中的案例分析.东南大学学报:哲学社会科学版, Vol. 17, pp.170-171, 2015.

[18] Xian Shi, Jian Wang*, Gang Liu, Liu Yang, Xinmin Ge, Shu Jiang.Application of extreme learning machine and neural networks in total organic carbon content prediction in organic shale with wire line logs, Journal of Natural Gas Science and Engineering, Vol. 33, pp. 687-702, 2016. (通讯作者) (SCI 三区)

[19] Xiaoling Gong, Jian Wang*, Yanjiang Wang, and Jacek M. Zurada. A Conjugate Gradient-based Efficient Algorithm for Training Single-hidden-layer Neural Networks, The 23rd International Conference on Neural Information Processing (ICONIP), Vol. 9950, pp. 470-478, 2016. (EI)[20] Jian Wang, Zhenyun Ye, Weifeng Gao, Jacek M. Zurada. Boundedness and Convergence Analysis of Weight Elimination for Cyclic Training of Neural Networks,Neural Networks, Vol. 82, pp. 49-61, 2016. (SCI 二区)

[21] Xian Shi, Gang Liu, Yuanfang Cheng, Liu Yang, Hailong Jiang, Lei Chen, Shu Jiang, Jian Wang*. Brittleness index prediction in shale gas reservoirs based on efficient network models, Journal of Natural Gas Science and Engineering, Vol. 35, pp. 673-685, 2016. (通讯作者)(SCI 三区)

[22] Xian Shi, Gang Liu, Xiaoling Gong, Jialin Zhang, Jian Wang, and Hongning Zhang. An Efficient Approach for Real-Time Prediction of Rate of Penetration in Offshore Drilling, Mathematical Problems in Engineering, Vol. 3, pp. 1-13, 2016. (SCI 四区)

    [23] 王健.中外教师合作教学模式对师生的能力影响研究, 黑龙江教育学院学报, Vol. 35, No. 8, pp. 37-39, 2016.

    [24] Jian WangQingling Cai, Qingquan Chang, Jacek M. Zuradad. Convergence Analyses on Sparse Feedforward Neural Networks via Group Lasso Regularization,Information Sciences, Vol. 381, pp. 250-269, 2017.(SCI 二区)

[25] Xian Shi, Jian Wang*, Xinmin  Ge, Zhongying  Han, Guanzheng  Qu, Shu  Jiang. A new method for rock brittleness evaluation in tight oil formation from conventional logs and petrophysical data, Journal of Petroleum Science and Engineering,151 168-182, 2017.  (通讯作者) (SCI 三区)

[26] Jian Wang, Yanqing Wen, Yida Gou, Zhenyun Yeb, Hua Chen.Fractional-order gradient descent learning of BP neural networks with Caputo derivative, Neural Networks, 89: 19–30, 2017. (SCI 二区)

[27] Guoling Yang, Bingjie Zhang, Zhaoyang Sang, Jian Wang*, and Hua Chen. A Caputo-type Fractional-order gradient descent learning of BP neural networks, The 14th International Symposium on Neural Networks,  ISNN 2017. Lecture Notes in Computer Science, vol 10261, pp. 547-554, 2017 (通讯作者)(EI)

[28]  Jian Wang, Guoling Yang, Bingjie Zhang, Zhanquan Sun, Yusong Liu, Jichao Wang.Convergence analysis of Caputo-type fractional order complex-valued neural networks, IEEE Access, 5: 14560-14571, 2017. (SCI 四区)

[29] Jian Wang, Yanqing Wen, Zhenyun Ye, Ling Jian and Hua Chen. Convergence analysis of BP neural networks via sparse response regularization, Applied Soft Computing, 61: 354-363, 2017. (SCI 二区)

[30] Bingjie Zhang, Tao Gao, Long Li, Zhanquan Sun, and Jian Wang*. An Improved Conjugate Gradient Neural Networks Based on a Generalized Armijo Search Method, The 24th International Conference on Neural Information Processing (ICONIP 2017), Vol. 10637, pp. 131-139, 2017.(EI 通讯作者)

[31]  Qin Liu, Zhaoyang Sang, Hua Chen, Jian Wang, Huaqing Zhang*. An Efficient Algorithm for Complex-Valued Neural Networks Through Training Input Weights, The 24th International Conference on Neural Information Processing (ICONIP 2017), Vol. 10637, pp. 150-159, 2017. (EI)

[32]  Hongmin Gao, Yichen Yang, Bingyin Zhang, Long Li, Huaqing Zhang, and Shujun Wu*. Feature Selection Using Smooth Gradient L1/2 Regularization, The 24th International Conference on Neural Information Processing (ICONIP 2017), Vol. 10637, pp. 160-170, 2017.

[33] Jian Wang, Qingquan Chang, Qin Chang, Yusong Liu and Nikhil R. Pal. Weight noise injection-based MLPs with group lasso penalty: Asymptotic Convergence and application to node pruning, Submitted to IEEE Transactions on Cybernetics, 2017.

[34] Jian Wang, Bingjie Zhang, Zhanquan Sun, Wenxue Hao, Qingying Sun. A novel conjugate gradient method with generalized Armijo search for efficient training of feedforward neural networks, Neurocomputing, 275:308-316, 2018. doi.org/10.1016/j.neucom.2017.08.037(SCI 二区)

[35] Jian Wang, Chen Xu, Xifeng Yang, and Jacek M. Zurada, A Novel Pruning Algorithm for Smoothing Feedforward Neural Networks based on Group Lasso Method, In Press,IEEE Transactions on Neural Networks and learning Systems, 2018doi.org/10.1109/TNNLS.2017.2748585(SCI 一区)


★指导本科生:

2015届,金哲(中国科学院攻读硕士研究生),理学院优秀本科毕业设计论文;

2016届,张炳杰(保送研究生),校级优秀本科毕业设计论文;

2017届,谢雪涛,俞灵,王珊珊

★指导硕士研究生:

2012级常清泉, 兰州大学数学学院硕士(2014.02-2015.02,协助指导);

2014级温艳青、龚晓玲

2015级杨国玲

2016级张炳杰、刘芹、朱明月

2017级谢雪涛、俞灵

★指导博士研究生:

2016级高涛,(副导师, 协助Jacek M. Zurada 院士指导)