Statistical Methods for Intelligent Information Processing (3 credits)


Instructor: Prof. Shou-de Lin ( , Office 333

Classroom: CSIE 111

Meeting Time: Tue 14:20-17:20 pm

Office Hour:  After class or by appointment


Course Description:

This course teaches how to process information intelligently using statistical methods and algorithms. 


Programming Assignments: (60%)
Final Project: (40%)

Reference books:

Elements of Statistical Learning by Trevor Hastie, Robert Tibshirani and Jerome Friedman (ISBN 0387952845)
Pattern Recognition and Machine Learning by Chris Bishop (SBN 0387310738)
Machine Learning by Tom Mitchell (ISBN 0070428077)
The EM algorithm and related statistical models / edited by Michiko Watanabe, Kazunori Yamaguchi
Reinforcement learning : an introduction / Richard S. Sutton and Andrew G. Barto MIT Press, c1998

Syllabus (tentative):

16-Sep introduction+Basic 
  Supervised Learning 
23-Sep Regression, DT, ME
30-Sep VC dimension, SVM, Lazy Learning
7-Oct HMM, , Bayesian
14-Oct Imbalanced Data Classification
  Unsupervised Learning 
21-Oct LM+viterbi
28-Oct EM
4-Nov EM+clustering
11-Nov Labelling
  Reinfocement learning
18-Nov Monte Carlo, MDP
25-Nov Q-learning
2-Dec Project Proposal
  Machine Discovery
16-Dec Advanced LM
23-Dec Discovery in Social Network
30-Dec Advanced topics in KDD
6-Jan Final Project Presentation
13-Jan Final Project Presentation