Syllabus data
|
Teacher name ： CHANDRASIRI Naiwala Pathirannehelage
|
Academic year
2025Year
Term
Second Semester
Course title
Pattern Recognition
Class type
Lecture
Course title (ENG)
Pattern Recognition
Class code・Class name・Teaching forms
Z1600001 Pattern Recognition
Instructor
CHANDRASIRI Naiwala Pathirannehelage
Credits
2.0Credits
Day and Time
Thu.4Period
Campus
Shinjuku Campus
Location
A-0762教室
Relationship between diploma policies and this course
A) A high degree of specialized expertise 70%
B) The skills to use science and technology 30% C) The ability to conduct research independently, knowledge pertaining to society and occupations, and sense of ethics required of engineers and researchers 0% D) Creative skills in specific areas of specialization 0% Goals and objectives
Pattern recognition is one of the basic technologies for efficient processing of various media such as images, voices or documents and extracting necessary information from them automatically. Representative examples of pattern recognition technologies that are currently used include face recognition and postal code recognition. In this course on pattern recognition, our goal is to understand pattern recognition technologies and to be able to implement some of its key methods. Here, we specially focus on deep learning, which has attracted attention recently.
Prerequisites
Nothing special.
Method Using AL・ICT
Project Based Learning／Support for self-learning using ICT
Class schedule
Each year, the contents that cover in the lectures depend on the students' interests and understanding of the subject.
We focus on understanding and implementation of pattern recognition algorithms in this lecture. Lecture Plan １ ： Introduction ２ ： Pattern Recognition・Machine Learning (ⅰ) ３ ： Pattern Recognition・Machine Learning (ⅱ) ４ ： Artificial Neural Networks (ⅰ) ５ ： Artificial Neural Networks (ⅱ) ６ ： Training of Multi-Layer Neural Networks (ⅰ) 7 ： Training of Multi-Layer Neural Networks (ⅱ) ８ ： Neural Networks and Classification (ⅰ) ９ ： Neural Networks and Classification (ⅱ) １０ ： Deep Learning (ⅰ) １1 ： Deep Learning (ⅱ) １２ ： Convolution Neural Network (ⅰ) １３ ： Convolution Neural Network (ⅱ) １４ ： Handwritten Digit Recognition - Presentation of the Experimental Results There will be no examinations. Evaluation
Grade evaluation is done based on active participation at the classes and submitted reports（50％）, Final presentation and final report（50％）.
Feedback for students
We will inform the feed back method via the KU-LMS.
Textbooks
Related materials that are used in the class will be distributed electronically.
Reference materials
Phil Kim, MATLAB Deep Learning: With Machine Learning, Neural Networks and Artificial Intelligence 1st Edition, ISBN-13: 978-1484228449, ISBN-10: 1484228448
Office hours and How to contact teachers for questions
Office hours: 13:30-14:30 Thursday @ A1513
Message for students
Course by professor with work experience
Applicable
Work experience and relevance to the course content if applicable
自動車関連のIT企業での知能情報システムを提案・プロトタイプ開発の経験がある教員が、機械学習・深層学習に関する経験を活かし、パターン認識（機械学習）について講義する。
Teaching profession course
Department of Information Design
|
