Hiroshima University Syllabus

Back to syllabus main page
Academic Year 2022Year School/Graduate School School of Informatics and Data Science
Lecture Code KA208001 Subject Classification Specialized Education
Subject Name 人工知能と機械学習
Subject Name
Subject Name in
Artificial Intelligence and Machine Learning
クリタ タキオ
Campus Higashi-Hiroshima Semester/Term 3rd-Year,  Second Semester,  3Term
Days, Periods, and Classrooms (3T) Weds5-8:ENG 103
Lesson Style Lecture Lesson Style
(More Details)
Lecture using PC projector 
Credits 2.0 Class Hours/Week   Language of Instruction B : Japanese/English
Course Level 3 : Undergraduate High-Intermediate
Course Area(Area) 25 : Science and Technology
Course Area(Discipline) 02 : Information Science
Eligible Students
Keywords pattern recognition, machine learning, neural networks 
Special Subject for Teacher Education   Special Subject  
Class Status
within Educational
Criterion referenced
Integrated Arts and Sciences
(Knowledge and Understanding)
・Knowledge and understanding of the importance and characteristics of each discipline and basic theoretical framework.

Program of Electrical,Systems and Information Engineering
(Abilities and Skills)
・Concepts, knowledge and methods which are the basis for studies related to electrical, systems, and information engineering.

Informatics and Data Science Program
(Knowledge and Understanding)
・I1. Knowledge and ability required for collecting and processing high-dimensional data using information processing technologies based on scientific logic, while understanding the theoretical system that forms the basis of informatics.
Class Objectives
/Class Outline
Artificial intelligence is an attempt to artificially imitate the function of the human brain. Data mining that extracts useful information from the enormous data accumulated on the Internet is also becoming popular. Machine learning provides the technical basis of these applications and automatically determine model parameters from training samples. This course will focus on basic topics on Machine Learning and Pattern Recognition. 
Class Schedule lesson1 Introduction and Mathmetical Foundations
lesson2 Basics of Probabilities and Statistics
lesson3 Bayes's Decition Theory
lesson4 Programming Environment for Machine Learning
lesson5 Linear Models for Classification
lesson6 Linear Models for Regression
lesson7 Generalization
lesson8 Presentation and Discussion
lesson9 Information Extraction
lesson10 Kernel Learning
lesson11 Clustering
lesson12 Neural Networks and Deep Neural Networks
lesson13 Other Machine Learning Methods
lesson14 Applications of Machine Learning
lesson15 Final Presentation and Discussion

Reports and Presentations 
C.M.Bisop, Pattern Recognition and Machine Learning, Springer

T.Hastie, R.Tibshirani, and J.Friedman, The Elements of Statistical Learning, Springer 
PC or AV used in
(More Details) Projector 
Learning techniques to be incorporated  
Suggestions on
Preparation and
Please read the related text books by yourself 
Grading Method Reports (about 70%) and others such as Presentations, Quiz, etc. (about 30%) 
Practical Experience  
Summary of Practical Experience and Class Contents based on it  
Please fill in the class improvement questionnaire which is carried out on all classes.
Instructors will reflect on your feedback and utilize the information for improving their teaching. 
Back to syllabus main page