Track Listing

Up one level

Personal Items by zadmin — last modified 2003-11-22 05:34 PM

contains personal workarea items for caner

yongjoonyang's Home by zadmin — last modified 2007-05-06 09:18 PM

Home page area that contains the items created and collected by yongjoonyang

yongjoonyang's Home Page by YongJoon Yang — last modified 2007-05-06 09:18 PM

yongjoonyang's front page

Personal Items by zadmin — last modified 2003-11-22 06:21 PM

contains personal workarea items for yongjoonyang

kmkrebs's Home by zadmin — last modified 2007-05-07 10:48 AM

Home page area that contains the items created and collected by kmkrebs

kmkrebs's Home Page by k.m.krebs — last modified 2007-05-07 10:48 AM

kmkrebs's front page

Personal Items by zadmin — last modified 2003-11-23 05:59 AM

contains personal workarea items for kmkrebs

klaus's Home by zadmin — last modified 2007-05-06 09:18 PM

Home page area that contains the items created and collected by klaus

klaus's Home Page by klaus voltmer — last modified 2007-05-06 09:18 PM

klaus's front page

Personal Items by zadmin — last modified 2003-11-23 12:27 PM

contains personal workarea items for klaus

fh's Home by zadmin — last modified 2007-05-07 10:48 AM

items created and collected by fh

fh by Frank Hausman — last modified 2007-05-07 10:48 AM

fh

Personal Items by zadmin — last modified 2003-11-23 09:41 PM

contains personal workarea items for fh

MyPortrait by Frank Hausman — last modified 2007-05-06 02:36 PM

 

files by zadmin — last modified 2007-05-06 09:32 PM

files

x-arithmetic.c with xor [^] added by Frank Hausman — last modified 2007-05-06 02:36 PM

x-arithmetic with xor [^] added.

Karl MacMillan's knn by Frank Hausman — last modified 2007-05-06 06:42 PM

In the mail archives, Karl MacMillan wrote: "I have posted an implementation of the k-NN algorithm as a pd object to my website: http://mambo.peabody.jhu.edu/~karlmac/download/pd/knn.tar.gz [dead link] There is a help patch and a readme, but they are probably not that much help. Feel free to ask me questions. The general idea is that objects can be classified by their feature vector (just a pd list of floating point numbers - the numbers can refer to anything i.e. size, shape, spectral features, etc.). You train the classifier by inputting known feature vectors. After the training is complete you can input an unknown feature vector which will be assigned the same classification as the majority of the k (k is a small number like 3 or 5) closest feature vectors in the database (nearest neighbors). The classification is pretty quick as the entire database is in ram and is usually pretty small (a few hundred to a few thousand). This implementation also has the ability to weight features - that is give more importance to a certain feature. This is done with a vector the same size as the feature vector with weights between 0 and 1. The default is to treat all of the features equally. I have some code that will determine the optimum weights for a database using a genetic algorithm - I will release this after I clean it up a bit. Here at Peabody we have used a k-NN classifier to successfully recognize sheet music (http://mambo.peabody.jhu.edu/omr) and timbre (I will post papers about this soon). At this point I should give credit to Dr. Ichiro Fujinaga who has done most of this research - I am his graduate student and helped with the implementation and some of the research, but he is the one that deserves most of the credit. One problem with the current implementation is the the length of the feature vectors and the maximum number of classes is fixed at compile time. If this is really a problem for anyone let me know. Karl" The file was downloaded from Karl MacMillan's http://pix.test.at/tmp/knn.tar.gz courtesy pix

artelse's Home by zadmin — last modified 2007-05-07 10:48 AM

Home page area that contains the items created and collected by artelse

artelse's Home Page by Arthur Elsenaar — last modified 2007-05-07 10:48 AM

artelse's front page

Personal Items by zadmin — last modified 2003-11-23 11:25 PM

contains personal workarea items for artelse