文件列表:

MIMLAnnotator (0, 2010-07-13)
MIMLAnnotator\codes (0, 2010-07-13)
MIMLAnnotator\codes\demo_data (0, 2010-07-13)
MIMLAnnotator\codes\demo_data\demoBags.mat (467945, 2010-07-13)
MIMLAnnotator\codes\demo_data\idx_3_10.mat (982, 2010-07-13)
MIMLAnnotator\codes\demo_data\kernel_3.mat (73212, 2010-07-13)
MIMLAnnotator\codes\EMIMLSVM+ (0, 2010-07-13)
MIMLAnnotator\codes\EMIMLSVM+\build_mi_kernel.m (2445, 2010-07-13)
MIMLAnnotator\codes\EMIMLSVM+\build_multi_task_classifiers.m (4766, 2010-07-12)
MIMLAnnotator\codes\EMIMLSVM+\classify_multi_task_miml.m (1618, 2009-08-30)
MIMLAnnotator\codes\EMIMLSVM+\function_eval (0, 2010-07-12)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\auroc.m (2283, 2008-08-20)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\avg_precious.m (1001, 2009-06-13)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\coverage.m (744, 2008-10-26)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\evaluate_miml.m (2203, 2009-12-27)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\getAUC.m (1356, 2009-06-22)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\getF1.m (2880, 2009-08-31)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\getHamming_loss.m (522, 2009-06-04)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\one_error.m (712, 2008-09-03)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\ranking_loss.m (911, 2008-09-03)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\roc.m (2456, 2008-08-20)
MIMLAnnotator\codes\EMIMLSVM+\function_eval\rocch.m (3027, 2008-08-20)
MIMLAnnotator\codes\EMIMLSVM+\get_task_cluster_km.m (2031, 2010-07-12)
MIMLAnnotator\codes\EMIMLSVM+\Main_Build_miKernel.m (370, 2010-07-12)
MIMLAnnotator\codes\EMIMLSVM+\Main_MIMLSVM.m (4651, 2010-07-13)
MIMLAnnotator\codes\EMIMLSVM+\make_multi_task_model.m (2591, 2009-12-30)
MIMLAnnotator\codes\libsvm_ci (0, 2010-07-13)
MIMLAnnotator\codes\libsvm_ci\COPYRIGHT (1497, 2009-02-17)
MIMLAnnotator\codes\libsvm_ci\libsvmread.mexw32 (20480, 2009-10-04)
MIMLAnnotator\codes\libsvm_ci\libsvmread.mexw32.pdb (282624, 2009-10-04)
MIMLAnnotator\codes\libsvm_ci\libsvmread.mexw64 (11264, 2009-10-09)
MIMLAnnotator\codes\libsvm_ci\libsvmwrite.mexw32 (19456, 2009-10-04)
MIMLAnnotator\codes\libsvm_ci\libsvmwrite.mexw32.pdb (282624, 2009-10-04)
MIMLAnnotator\codes\libsvm_ci\libsvmwrite.mexw64 (10240, 2009-10-09)
MIMLAnnotator\codes\libsvm_ci\svm.mexw32.pdb (77824, 2009-10-04)
MIMLAnnotator\codes\libsvm_ci\svmpredict.mexw32 (91136, 2009-10-04)
MIMLAnnotator\codes\libsvm_ci\svmpredict.mexw32.pdb (446464, 2009-10-04)
MIMLAnnotator\codes\libsvm_ci\svmpredict.mexw64 (24576, 2009-10-09)
MIMLAnnotator\codes\libsvm_ci\svmtrain.mexw32 (95232, 2009-10-04)
... ...

------------------------------------------------------------------------------------------ Readme for the MIML leanring based Annotationg Package MIMLAnnotator version July 7, 2010 ------------------------------------------------------------------------------------------ The package includes the MATLAB code of MIMLSVM+, E-MIMLSVM+ which addresses the problems of multi-instance multi-label learning. Refer: [1] Y.-X. Li, S. Ji, J. Ye, S. Kumar, and Z.-H. Zhou. Drosophila gene expression pattern annotation through multi-instance multi-label learning. Submitted to IEEE/ACM Transcations on Computational Biology and Bioinformatics. To demonstate the main steps of MIMLSVM+ and E-MIMLSVM+, (1) you can run 'matlab>> ./codes/MIMLSVM/Main_Build_miKernel;' to demonstrate the process of calculating the multi-instance kernel; (2)you can run 'matlab>> ./codes/MIMLSVM/Main_MIMLSVM(1);' to demonstrate the annotaton process of MIMLSVM+, or run 'matlab>> ../codes/MIMLSVM/Main_MIMLSVM(0.5);' to implement E-MIMLSVM+ with the sactter ratio equal to 0.5. All the program are developed under Microsoft windows with Matlab 7.6. So, if you want to run these codes, please make sure the software environments. Note[1]: the datasets provided in './demo_data' are artifical data sets just used for demonstration, not the real world data of FlyExpress. Therefore, the bags, kernel, labels, and the accuracy obtained are all meaningless. Therefore, it is also meaningless to compare the results of MIMLSVM+ and E-MIMLSVM+ on these data. It is just used to show the orgnization of samples, and how to call the functions to do annotation. Thus, please do not use these data for any experiments. Note[2]: the Matlab version of Libsvm (available at http://www.csie.ntu.edu.tw/~cjlin/libsvm/, version 2.89) is modified, you can find it at './libsvm_ci/'. For the original libsvm, refer: [2] C.-C. Chang and C.-J. Lin. Libsvm: A library for support vector machines, Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan, Technical Report, 2001. ATTN: - This package is free for academic usage. You can run it at your own risk. For other purposes, please contact Prof. Zhi-Hua Zhou (zhouzh@nju.edu.cn). - This package was developed by Dr. Ying-Xin Li (liyx@lamda.nju.edu.cn). For any problem concerning the code, please feel free to contact Dr. Li. ------------------------------------------------------------------------------------------

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：