Graduate School of Science and Engineering

Back to List

HUI500X4(人間情報学 / Human informatics 500)
Intelligence Acquisition

Jianquan LIU

Class code etc
Faculty/Graduate school Graduate School of Science and Engineering
Attached documents
Year 2023
Class code YC034
Previous Class code
Previous Class title
Term 春学期授業/Spring
Day/Period 月4/Mon.4
Class Type
Campus 小金井
Classroom name 各学部・研究科等の時間割等で確認
Grade
Credit(s) 2
Notes
Class taught by instructors with practical experience
Category システム理工学専攻

Show all

Hide All

Outline (in English)

[Abstract]

In this course, a series of technologies for information processing and knowledge acquisition focusing on big data will be introduced, including the core fundamental theories and practical techniques for data mining. During the whole course, the fundamental theory related to knowledge discovery will be introduced first. Then, the practical techniques for information retrieval, link analysis, web or text data analysis, and other methods for knowledge acquisition, will be introduced. Finally, recent research topics related to AI, Big Data, and IoT will be introduced as extended knowledge.

[Objectives / Goals]

The objective of knowledge acquisition is to learn the fundamentals and the practical skills of data mining techniques, including association rule & pattern, supervised learning, unsupervised learning, semi-supervised learning, information retrieval, and web search. Furthermore, the objective also includes the related skills for surveying the latest research papers regarding data mining and big data processing, and the presentation skills for introducing the approaches and related contents presented in those papers after the survey phase.

[Methods]

In this course, the fundamentals of data mining techniques including association rule & pattern, supervised learning, unsupervised learning, semi-supervised learning, information retrieval and web search, will be introduced. Practical exercises will be conducted to apply the previous fundamental techniques to solve real problems for better understanding of those theories, technologies, and algorithms.

Subsequently, the data mining techniques focusing on web data, including social network analysis, web crawling, link analysis, structure data extraction, information integration, opinion mining, sentiment analysis, and recommendation system, will be introduced in this course as well.

Finally, the students will be asked to apply all learned data mining techniques to solve real problems, to survey the latest research papers related to big data processing that have been published at the recent five years in the proceedings of major international conferences and journals, and to give a presentation to introduce the latest techniques or approaches introduced in those papers.

[Work to be done outside of class]

All lecture notes are created in English. The students are requested to read the lecture notes that were delivered at previous lecture in advance in order to have basic understanding on the contents. In some lectures, the students need to do a presentation using PowerPoint o introduce the surveyed papers, thus please learn how to use PowerPoint in advance. For the purpose of paper survey and presentation, extra time for reviewing the lecture notes (around 4 hours), reading the lecture notes in advance (around 4 hours), intensive reading of literature, and preparing presentation materials, will be required after the lecture time.

[Textbooks]

Not require to buy any extra textbooks. Lecture notes will be delivered in each lecture.

[References]

- Bing Liu: "Web Data Mining -- Exploring Hyperlinks, Contents, and Usage Data". Second Edition, July 2011. Springer.
- Jure Leskovec, Anand Rajaraman, Jeff Ullman: "Mining of Massive Datasets". Second Edition, March 2014. Cambridge University Press. (Chapter 9)
- Proceedings of conferences: KDD/ICDM/SIGMOD/VLDB/ICDE 2018-2022.

[Grading criteria]

The grading criteria include the evaluations on the submitted final reports, the reaction of Q&A in the course, the presentation of surveyed papers, and the regular attendance. The overall grade is composed of the following percentages on each criterion.

- Regular attendance (30%)
- Presentation of surveyed papers (30%)
- Final reports (30%)
- Reaction of Q&A in the course (10%)

[Changes following student comments]

All contents introduced in this course are more at the practical perspective rather than theoretical only, and all lecture notes are prepared in English. Based on the evaluations by the students in the past years, this course is recognized as very good opportunity for learning English and practical technologies related to AI and Big Data. Therefore, this year, all lectures of this course will be instructed in the same way as previous years.

[IT equipment]

A laptop or PC with Internet connection will be used for attending online lectures (in case), paper survey and presentation in the course.

[Others]

This year, the course will be instructed in-person to increase the ration of concentration and comprehension during the lectures. It will be an option to change to online (Zoom) course when the COVID-19 situation would be getting worse. In the first lecture, the students' IT environments will be confirmed by the instructor to guarantee everyone can fairly attend the online lectures. In some cases, using Teams as an online tool will be an alternative.

Default language used in class

日本語 / Japanese