Pattern Recognition Technology
TeachersYAMANE, KenStaffInfo
Grade, SemesterYear 3 1st semest [Department of Information and Electronic Engineering, Faculty of Science and Engineering]
CategorySpecial Subjects
Elective, CreditsElective 2credit
 Syllabus Number3D325

Course Description

The main topics are as follows: linear models for regression, linear models for classification, neural networks.

Course Objectives

The aim of the course is to learn fundamental methods and techniques of pattern recognition.

Grading Policy

Students are evaluated with reports in each lecture (30%), a mid-term exam (30%), and a term exam (40%).

Textbook and Reference

KindTitleAuthorPublisher
TextbookNo textbook is used.
References

Requirements(Assignments)

Note

Schedule

1Introduction
2Template matching, prototype, nearest-neighbor method
3Least squares method
4Linear discriminant, linear regression, logistic regression
5Bayesian inference, maximum likelihood
6Clustering: k-means clustering, Gaussian mixture model (GMM), expectation-maximization algorithm (EM algorithm)
7Time series pattern recognition: matching algorithm based on dynamic programming (DP matching), hidden Markov model (HMM)
8Summary, mid-term exam
9Radial basis function network (RBFN)
10Support vector machine (SVM), support vector regression (SVR)
11Neural networks I: recurrent neural network, Hopfield model
12Neural networks II: perceptron, leaning rules
13Neural networks III: Multi-layer neural network (Multilayer perceptron, MLP), backpropagation algorithm, deep neural network (DNN)
14State-of-the-art technology: Deep learning (CNN, R-CNN, fast R-CNN, faster R-CNN, mask R-CNN, etc.)
15Summary, term exam