第4期 赵壮壮，等：任务间共享和特有结构分解的多任务TSK模糊系统建模 ·629· Journal of machine learning research,2010,11(5): [23]LIU Guangcan,LIU Zhouchen,YAN Shuicheng.Robust 2901-2934 recovery of subspace structures by low-rank representa- [13]EVGENIOU T,MICCHELLI C A,PONTIL M.Learning tion[J].IEEE transactions on pattern analysis and ma- multiple tasks with kernel methods[J].Journal of ma- chine intelligence,2013,35(1):171-184. chine learning research,2005,6(4):615-637. [24]JIANG Pengbo,WANG Xuetong,LI Qiongling,et al. [14]ZHANG Jiangmei,YU Binfeng,JI Haibo,et al.Multi- Correlation-aware sparse and low-rank constrained multi- task feature learning by using trace norm regulariza- task learning for longitudinal analysis of alzheimer's dis- tion[J].Open physics,2017,15(1):674-681. ease[J].IEEE journal of biomedical and health informat- [15]ZHAO Qian,RUI Xiangyu,HAN Zhi,et al.Multilinear ics,2019.23(4:1450-1456. multitask learning by rank-product regularization[J]. [25]ZHOU Jiayu,CHEN Jianhui,YE Jieping.Malsar:multi- IEEE transactions on neural networks and learning sys- task learning via structural regularization-user's manual tems,2020,31(4):1336-1350. version1.1[EB/OL].(2019-12-12)[2020-07-08]https:/github [16]ZHONG Shi,PU Jian,JIANG Yugang,et al.Flexible com/jiayuzhou/MALSAR. multi-task learning with latent task grouping[J].Neuro- [26]JUANG C F,CHIU S H,SHIU S J.Fuzzy system learned computing,2016,189:179-188. through fuzzy clustering and support vector machine for [17]XUE Ya,LIAO Xuejun,CARIN L,et al.Multi-task human skin color segmentation[J].IEEE transactions on learning for classification with dirichlet process priors[J]. systems,man,and cybernetics-part A:systems and hu- Journal of machine learning research,2007,8:35-63. mans,2007,37(6):1077-1087 [18]JIANG Yizhang,DENG Zhaohong,CHUNG F L,et al. 作者简介： Multi-task TSK fuzzy system modeling using inter-task 赵壮壮，硕士研究生，主要研究方 correlation information[J].Information sciences,2015, 向为模式识别与人工智能、模糊系统。 298:512-533 [19]WANG Jun,LIN Defu,DENG Zhaohong,et al.Multi- task TSK fuzzy system modeling by jointly reducing rules and consequent parameters[J].IEEE transactions on sys- tems,man,and cybernetics:systems,2019. [20]MENG Fan,YANG Xiaomei,ZHOU Chenghu,et al.The 王骏，副教授，主要研究方向为机 augmented lagrange multipliers method for matrix com- 器学习、模糊系统、医学影像分析。 pletion from corrupted samplings with application to mixed gaussian-impulse noise removal[J].PLoS one, 2014,9(9):e108125. [21]LIN Zhouchen,LIU Risheng,SU Zhixun.Linearized al- ternating direction method with adaptive penalty for low- rank representation[C]//Proceedings of 25th Annual Con- 潘祥，副教授、主要研究方向为医 学图像诊断、计算机视觉、AI医疗诊 ference on Neural Information Processing Systems. 断。主持国家自然科学基金项目 Granada,Spain,2011:612-620. 1项，安徽省自然科学基金项目1项。 [22]CAI Jianfeng,CANDES E J,SHEN Zuowei.A singular 获得授权发明专利6项，受理发明专 value thresholding algorithm for matrix completion[J]. 利2项。发表学术论文20余篇。 SIAM journal on optimization,2010,20(4):1956-1982.Journal of machine learning research, 2010, 11(5): 2901–2934. EVGENIOU T, MICCHELLI C A, PONTIL M. Learning multiple tasks with kernel methods[J]. Journal of ma￾chine learning research, 2005, 6(4): 615–637. [13] ZHANG Jiangmei, YU Binfeng, JI Haibo, et al. Multi￾task feature learning by using trace norm regulariza￾tion[J]. Open physics, 2017, 15(1): 674–681. [14] ZHAO Qian, RUI Xiangyu, HAN Zhi, et al. Multilinear multitask learning by rank-product regularization[J]. IEEE transactions on neural networks and learning sys￾tems, 2020, 31(4): 1336–1350. [15] ZHONG Shi, PU Jian, JIANG Yugang, et al. Flexible multi-task learning with latent task grouping[J]. Neuro￾computing, 2016, 189: 179–188. [16] XUE Ya, LIAO Xuejun, CARIN L, et al. Multi-task learning for classification with dirichlet process priors[J]. Journal of machine learning research, 2007, 8: 35–63. [17] JIANG Yizhang, DENG Zhaohong, CHUNG F L, et al. Multi-task TSK fuzzy system modeling using inter-task correlation information[J]. Information sciences, 2015, 298: 512–533. [18] WANG Jun, LIN Defu, DENG Zhaohong, et al. Multi￾task TSK fuzzy system modeling by jointly reducing rules and consequent parameters[J]. IEEE transactions on sys￾tems, man, and cybernetics: systems, 2019. [19] MENG Fan, YANG Xiaomei, ZHOU Chenghu, et al. The augmented lagrange multipliers method for matrix com￾pletion from corrupted samplings with application to mixed gaussian-impulse noise removal[J]. PLoS one, 2014, 9(9): e108125. [20] LIN Zhouchen, LIU Risheng, SU Zhixun. Linearized al￾ternating direction method with adaptive penalty for low￾rank representation[C]//Proceedings of 25th Annual Con￾ference on Neural Information Processing Systems. Granada, Spain, 2011: 612−620. [21] CAI Jianfeng, CANDÈS E J, SHEN Zuowei. A singular value thresholding algorithm for matrix completion[J]. SIAM journal on optimization, 2010, 20(4): 1956–1982. [22] LIU Guangcan, LIU Zhouchen, YAN Shuicheng. Robust recovery of subspace structures by low-rank representa￾tion[J]. IEEE transactions on pattern analysis and ma￾chine intelligence, 2013, 35(1): 171–184. [23] JIANG Pengbo, WANG Xuetong, LI Qiongling, et al. Correlation-aware sparse and low-rank constrained multi￾task learning for longitudinal analysis of alzheimer’s dis￾ease[J]. IEEE journal of biomedical and health informat￾ics, 2019, 23(4): 1450–1456. [24] ZHOU Jiayu, CHEN Jianhui, YE Jieping. Malsar: multi￾task learning via structural regularization—user’s manual version 1.1[EB/OL]. (2019-12-12) [2020-07-08] https://github. com/jiayuzhou/MALSAR. [25] JUANG C F, CHIU S H, SHIU S J. Fuzzy system learned through fuzzy clustering and support vector machine for human skin color segmentation[J]. IEEE transactions on systems, man, and cybernetics-part A: systems and hu￾mans, 2007, 37(6): 1077–1087. [26] 作者简介： 赵壮壮，硕士研究生，主要研究方 向为模式识别与人工智能、模糊系统。 王骏，副教授，主要研究方向为机 器学习、模糊系统、医学影像分析。 潘祥，副教授、主要研究方向为医 学图像诊断、计算机视觉、AI 医疗诊 断。主持国家自然科学基金项 目 1 项，安徽省自然科学基金项目 1 项。 获得授权发明专利 6 项，受理发明专 利 2 项。发表学术论文 20 余篇。 第 4 期 赵壮壮，等：任务间共享和特有结构分解的多任务 TSK 模糊系统建模 ·629·