Electrical and Computer Engineering, NUS
Pattern recognition deals with automated classification, identification, and/or characterizations of signals/data from various sources. The main objectives of this graduate module are to equip students with knowledge of common statistical pattern recognition (PR) algorithms and techniques. Upon completion of this module, students will be able to analyze a given pattern recognition problem, and determine which standard technique is applicable, or be able to modify existing algorithms to engineer new algorithms to solve the problem.
Please note, this website covers only the 1st half of the course.
Textbooks:The following schedule will not be strictly followed.
Date | | |
---|---|---|
August 17 |
1. INTRODUCTION + LEAST SQUARE REGRESSION
Reading:
|
Lecture note 1
Logistics |
August 24 |
2. BAYESIAN INFERENCE
Reading:
| Lecture note 2 |
August 31 |
3. MLE + MAP FOR REGRESSION
Reading:
|
See Lecture note 2
Assignment 1 (CA1) |
September 7 |
4. FULL BAYESIAN FOR REGRESSION
Reading:
| Lecture note 4 |
September 14 |
5. PREDICTIVE DISTRIBUTION (REGRESSSION) + INTRO TO CLASSIFICATION
Reading:
| Lecture note 5 |
September 21 |
6. BAYESIAN INFERENCES FOR CLASSIFICATION
Reading:
| Lecture note 6 |
September 28 |
RECESS WEEK
|