Archived News

 

March 24  2006

bulletProject 1 due today.
bulletClustering example papers are:
bulletHierarchical Clustering: M. B. Eisen, P. T. Spellman, P. O. Brown, and D. Botstein, "Cluster analysis and display of genome-wide expression patterns," Proceedings National Academy of Science, vol. 95, pp. 14863-14868, 1998
bulletSelf-Organizing Maps: P. Tamayo, D. Slonim, J. Mesirov, Q. Zhu, S. Kitareewan, E. Dmitrovsky, E. S. Lander, and T. R. Golub, "Interpreting patterns of gene expression with self-organizing maps: Methods and application to hematopoietic differentiation," PNAS, vol. 96, pp. 2907-2912, 1999.
bulletSelf organizing Map Java Demo

February  24  2006

bulletProject 1 Description is partially up on the project page, details will follow.
bulletSVM Demo code is posted on the PR links page under SVM Topic

February  13  2006

bulletHomework 2 will be due on Wed. Feb 15. To change the parameter C in LIBSVM, use the parameter -c in the string:

        model = svmtrain(train_y,train_data,'-t 0 -b 1 -c 5');% sets C=5

List of all libsvm options:

-s svm_type : set type of SVM (default 0)
	0 -- C-SVC
	1 -- nu-SVC
	2 -- one-class SVM
	3 -- epsilon-SVR
	4 -- nu-SVR
-t kernel_type : set type of kernel function (default 2)
	0 -- linear: u'*v
	1 -- polynomial: (gamma*u'*v + coef0)^degree
	2 -- radial basis function: exp(-gamma*|u-v|^2)
	3 -- sigmoid: tanh(gamma*u'*v + coef0)
-d degree : set degree in kernel function (default 3)
-g gamma : set gamma in kernel function (default 1/k)
-r coef0 : set coef0 in kernel function (default 0)
-c cost : set the parameter C of C-SVC, epsilon-SVR, and nu-SVR (default 1)
-n nu : set the parameter nu of nu-SVC, one-class SVM, and nu-SVR (default 0.5)
-p epsilon : set the epsilon in loss function of epsilon-SVR (default 0.1)
-m cachesize : set cache memory size in MB (default 40)
-e epsilon : set tolerance of termination criterion (default 0.001)
-h shrinking: whether to use the shrinking heuristics, 0 or 1 (default 1)
-b probability_estimates: whether to train a SVC or SVR model for probability estimates, 0 or 1 (default 0)
-wi weight: set the parameter C of class i to weight*C, for C-SVC (default 1)

The k in the -g option means the number of attributes in the input data.

option -v randomly splits the data into n parts and calculates cross
validation accuracy/mean squared error on them.

 

February  5 2006

bulletHomework 2 is posted on the homework page.

January  23 2006

bulletHomework 1 Assignment: From textbook, 2.4,2.8. 2.28, 2.31 The last two problems are computer problems. You can use any language that you want. I suggest either R or Matlab. It is due on Jan 30 in class.

January  20 2006

bulletThe papers and text sections for the week will be given here and on the syllabus page.
bulletWeek 2 Topics: Decision functions and Bayesian decision theory, metrics
bulletNaive Bayes Classifiers, "On the Optimality of the Simple Bayesian Classifier under zero-one Loss", Domingos and Pazzani, Machine Learning, 1997; "An Empirical Study of the naive Bayes classifier," Rish in IJCAI-01 workshop on "Empirical Methods in AI". Also appeared as IBM Technical Report RC22230.
bulletApplication: Spam Detection

January  9 2006

bulletFirst meeting will be at 8 AM (way too early) in 1624 Howe, I would like to switch the class to two days/week, 1 hour 20 minute sessions if possible, but please bring schedule information.
bullet I will be traveling on Friday Jan 13, Ms. Joset Etzel will cover class on Friday at 8 AM in Howe 1246.

horizontal rule

Last Updated: 04/10/2006