摘要： 传统机器学习方法认为不同的学习任务彼此无关,但事实上不同的学习任务常常相互关联。迁移学习试图利用任务之间的联系以及过去的学习经验加速对于新任务的学习。将最小包含球(Minimum Enclosing Ball,MEB)算法与Parzen Windows概率估计公式相结合,提出了一种新的迁移学习算法MEBTL((Minimum Enclosing Ball Transfer Learning)。该算法同时结合CVM(Core Vector Machines)理论提出了CCMEBTL(Center Constrained Minimum Enclosing Ball Transfer Learning)算法,其可以在不同领域之间完成大样本的迁移学习。作为验证,将其应用在WIFI数据的室内定位、人脸识别检测上,并取得了较好的效果。
| [1] Dai W,Yang Q,Xue G,et al.Boostimg for transerfer learning[C]∥Proceedings of the 24th International Conference on Machine Learning．USA Corvasllis:ACM,2007:193-200 [2] Pan S J,Yang Q.A survey on transfer learning[J]．IEEE Transa-ctions on Knowledge and Data Engineering,2009,2(10):1345-1359 [3] Blitzer J,McDonald R,Percira F．Domain adaptation with structural correspondence learning[C]∥Processings of the 2006Conference on Empirical Methods in Natural Language Proces-sing．PA USA:SIAM,2006:120-128 [4] Hal Daum’e III．Daniel Mareu Domain adaptation for statistical classifiers[J].Journal of Artificial Intelligence Research,2006,6(4):101-126 [5] Blitzer J,Crammer K,Kulesza A,et al.Learning bounds for domain adaptation[C]∥Proceedings of the 21st Annual Confe-rence on Neural Information Processing Systems.Cambridge,MA:MIT,2008:129-136 [6] Dai W,Xue G,Yang Q,et al．Co-clustering based classification for out-of-domain documents[C]∥Proceedings of 13th ACM SIGKDD．New York:ACM,2007:210-219 [7] Tax D M J,Duin R P W．Support vector domain description[J]．Pattern Recognition Letters,1999,0(11):1191-1199 [8] Tsang I,Kwok J,Zurada J.Generlized core vector machines [J]．IEEE Transactions on Neural Networks,2006,7(5):1126-1139 [9] Tsang I,Kwok J,Cheung P．Core vector machines:Fast SVM training on very large data sets [J]．Journal of Machine Learning Research,2005,6(4):363-392 [10] Fang S-H,Lin T-N．Indoor location system based on discriminant-adaptive neural network in IEEE 802.11environments[J]．IEEE Transactions on Neural Networks,2008,19(11):1973-1978 [11] Yang Q,Pan S J,Zheng V W．Estimating location using Wi-Fi[J]．Intelligent Systems,IEEE,2008,3(1):8-13 [12] Satpal S,Sarawagi S．Domain Adaptation of Conditional Probability Models via Feature Subsetting [C]∥Proceedings of PKDD．Heidelberg:Springer-Verlag Press,2007,2:224-235 [13] Pan S J,Kwok J T,Yang Q．Transfer learning via dimensionality reduction[C]∥Proc.23rd Assoc.for the Advancement of Artificial Intelligence (AAAI) Conf.Artificial Intelligence．Chicago,IL,July 2008:677-682 [14] Pan S J,Tsang I W,Kwok J T,et al．Domain Adaptation viaTransfer Component Analysis [J]．IEEE Transactions on Neural Networks,2011,22(2):199-210 [15] Osuna E,Freund R,Giroal F．Training support vector machines:an application to face diction[C]∥Prceedings of IEEE Confe-rence on Computer Vision and Pattern Recognition．San Juan,1997:130-136 |
| No related articles found! |
|
||
首页