EE4389: Homework

Guidelines for homework report, pdf file.

Homework 1, pdf file, due Thursday 09/15.

• Solutions

Homework 2, pdf file, due Tuesday 10/04.

• Comments

• Solutions

Homework 3, pdf file, due Thursday 11/03.

• Timing of mutual funds

• Description of preprocessing

• Preprocessed data sets in .mat format

• Hints, updated on 10/30.

• Solutions

Homework 4, pdf file, due Tuesday 11/15.

• Data for Problem 1 in .cvs format

• Solutions

Homework 5, pdf file, due Tuesday 12/06.

• Do NOT use evalsvm for Problem 1 since evalsvm did not partition the data the way we prefer for the cross-validation. Use smo and svmclass, instead. Also implement your own cross-validation.

• To train the SVM classifier with polynomial kernel, use
  model = smo(data, struct('ker’, 'poly’, 'arg’, [q, 1], 'C’, c))
  where q is the degree of the polynomial and c is the regularization parameter . Note that we need q and 1 for the arguments. See help kernel in Matlab for more information.

• To predict on the given data, use
  ypred = svmclass(data.X, model)

• Solutions