MatlabSpiderToolbox

所属分类:matlab编程
开发工具:matlab
文件大小:2547KB
下载次数:17
上传日期:2009-11-13 23:57:06
上 传 者chenweihaobang3
说明:  Matlab人工智能学习包,由世界领先的德国马普所制作
(The spider is intended to be a complete object orientated environment for machine learning in Matlab. Aside from easy use of base learning algorithms, algorithms can be plugged together and can be compared with, e.g model selection, statistical tests and visual plots. This gives all the power of objects (reusability, plug together, share code) but also all the power of Matlab for machine learning research.)

文件列表:
MatlabSpiderToolbox\basic\@algorithm\algorithm.m (2941, 2004-03-31)
MatlabSpiderToolbox\basic\@algorithm\am_i_data.m (154, 2003-05-12)
MatlabSpiderToolbox\basic\@algorithm\display.m (1434, 2003-05-12)
MatlabSpiderToolbox\basic\@algorithm\display_simple.m (1526, 2003-05-12)
MatlabSpiderToolbox\basic\@algorithm\extract.m (2111, 2004-03-11)
MatlabSpiderToolbox\basic\@algorithm\gen.m (254, 2003-05-12)
MatlabSpiderToolbox\basic\@algorithm\get_name.m (155, 2004-03-26)
MatlabSpiderToolbox\basic\@algorithm\isdeferred.m (56, 2004-03-23)
MatlabSpiderToolbox\basic\@algorithm\subsasgn.m (3354, 2004-11-18)
MatlabSpiderToolbox\basic\@algorithm\subsref.m (2943, 2004-08-23)
MatlabSpiderToolbox\basic\@algorithm\test.m (2211, 2004-12-02)
MatlabSpiderToolbox\basic\@algorithm\train.m (3690, 2004-11-18)
MatlabSpiderToolbox\basic\@algorithm\traintest.m (3929, 2004-03-26)
MatlabSpiderToolbox\basic\@algorithm\traintests.m (437, 2003-05-12)
MatlabSpiderToolbox\basic\@chain\chain.m (1112, 2006-07-24)
MatlabSpiderToolbox\basic\@chain\display.m (1461, 2003-05-12)
MatlabSpiderToolbox\basic\@chain\subsasgn.m (3417, 2004-08-23)
MatlabSpiderToolbox\basic\@chain\subsref.m (2998, 2004-08-23)
MatlabSpiderToolbox\basic\@chain\testing.m (105, 2003-05-12)
MatlabSpiderToolbox\basic\@chain\training.m (249, 2003-05-12)
MatlabSpiderToolbox\basic\@cv\cv.m (2334, 2006-07-24)
MatlabSpiderToolbox\basic\@cv\display.m (1829, 2003-05-12)
MatlabSpiderToolbox\basic\@cv\get_name.m (372, 2003-05-12)
MatlabSpiderToolbox\basic\@cv\subsasgn.m (3418, 2004-08-23)
MatlabSpiderToolbox\basic\@cv\subsref.m (3007, 2004-08-23)
MatlabSpiderToolbox\basic\@cv\testing.m (640, 2003-05-12)
MatlabSpiderToolbox\basic\@cv\training.m (4370, 2006-02-08)
MatlabSpiderToolbox\basic\@data\concatenate.m (720, 2003-05-12)
MatlabSpiderToolbox\basic\@data\data.asv (2514, 2006-02-18)
MatlabSpiderToolbox\basic\@data\data.m (2569, 2006-07-24)
MatlabSpiderToolbox\basic\@data\display.m (706, 2005-05-18)
MatlabSpiderToolbox\basic\@data\get.m (684, 2006-05-31)
MatlabSpiderToolbox\basic\@data\get_dim.m (653, 2006-07-19)
MatlabSpiderToolbox\basic\@data\get_index.m (71, 2003-05-12)
MatlabSpiderToolbox\basic\@data\get_name.m (213, 2004-03-26)
MatlabSpiderToolbox\basic\@data\get_x.m (431, 2003-05-12)
MatlabSpiderToolbox\basic\@data\get_xy.m (420, 2003-05-12)
MatlabSpiderToolbox\basic\@data\get_y.m (388, 2003-05-12)
MatlabSpiderToolbox\basic\@data\isdeferred.m (35, 2004-11-08)
MatlabSpiderToolbox\basic\@data\partition.m (2294, 2003-08-12)
... ...

This is a template object, copying this directory and editing it should make it easy to create new objects. It implements a simple SVM for pattern recognition. The files are the following: template.m % constructor -- needs to include all hyperparameter and model % parameter declarations training.m % these two files are the core of any object -- they train testing.m % the algorithm given data and test the learnt model get_name.m % used for printing the name, you only need to edit this file % if you want to output special hyperparameters of your object % when the name is printed out subsref.m % used for getting parameters, you do not need to edit this file subsasgn.m% used for setting parameters, you do not need to edit this file PROGRAMMING GUIDELINES: 1) If you use a kernel, try to call train and test members of kernel, see e.g the svm object. This will help to make complex kernel objects, e.g feed_fwd networks of kernels. 2) always use get, get_x, set_x of data objects, and try not to create new data objects, otherwise you may lose e.g indexing information if you do not copy it -- see e.g svm object.

近期下载者

相关文件


收藏者