Pattern Recognition

Numbering Code U-ENG29 39122 LJ10
U-ENG29 39122 LJ12
Year/Term 2021 ・ Second semester
Number of Credits 2 Course Type Lecture
Target Year Target Student
Language Japanese Day/Period Wed.2
Instructor name KAWAHARA TATSUYA (Graduate School of Informatics Professor)
Outline and Purpose of the Course This course provides foundations of modeling and systems, which extract useful information for classification and prediction from real-world data. It covers a variety of machine learning techniques oriented for pattern recognition.
Course Goals to master basic approaches and major techniques of machine learning.
to be able to design a system for pattern classification and recognition.
Schedule and Contents 1. Introduction to pattern recognition
2. Discriminant function and machine capacity
3. Discriminant function based on Gaussian distribution
4. Clustering and Gaussian mixture model
5. DP matching and HMM (classification of sequential patterns)
6. Bayes classification
7. Naive Bayes classifier and logistic regression model
8. Perceptron learning of discriminant function
9. Neural network
10. Support vector machines (SVM)
11. Statistical feature extraction
12. Maximum likelihood estimation and regularization
13. Deep learning(1)
14. Deep learning(2); Pattern recognition systems
15. Examination and Feedback
Evaluation Methods and Policy The grading is based on the examination following the course, and some exercises provided in the course.
Course Requirements None
Study outside of Class (preparation and review) Excersize included in lecture slides
Textbooks Textbooks/References Lecture slides are provided via PandA CMS.