The aim of this course to introduce fundamental methods of machine learning and data mining, including Linear classification methods; Logistic regression and neural networks; Support vector machines; Random forests; Classification errors and regularization methods; Model selection and feature selection; Combining classifiers via boosting; Methods of Dimensionality reduction; Clustering algorithms; and Bayesian networks.
Students will be familiar and proficient with basic methods of machine learning and data mining, including knowledge of available software packages, and will be able to apply such methods to solve specific problems and interpret their outputs.
A student's grade in this course will be a weighted average of his/her performance on the homework assignments and the exams. The weights are as follows: performance on the homework assignments: 20%; performance on the midterm exam: 30%; performance on the final exam: 50%. Regular class attendance is required to pass the exam. Active class participation is highly recommended.