This image has been created by DALL E3 from the keywords "intelligent systems". It is not directly related to the content of the lecture.

Welcome to Intelligent systems!

This lecture will start on Oct. 17. Please wait for a while until the site is built.

This lecture is offered in the Department of Mathmatics, Physics, Electrical Engineering and Computer Sience, but it is a common course for the entire Graduate School of Engineering  Science, and is also included in the Applied AI Course of the Interfaculty Graduate School （IFGS)  program. Therefore, the number of students is very large (more than 100 last year). For this reason, we have decided to offer courses on demand, taking into consideration the need to secure classrooms and the need for students to travel to and from the classrooms.

As mentioned in the video above, the course material is in English, but the audio is in Japanese with English transcripts. I am still working on this through trial and error, so the method may change along the way.

Important general notifications about this class will also be sent via the LMS, but since some undergraduates do not have access to the system, any information will basically be posted on this page.

As well, In this lecture, we will also do some exercises. We will be using the free google colaboratory, so please make sure you have a google account.

Links to each class will be provided in the SCHEDULE at the bottom of this page. These pages are password protected. Please check the LMS for the password.

If you are an undergraduate student, please contact us by e-mail (hamagami@ynu.ac.jp).

Depending on the unit, content from the previous year may be reused. Please note that there may be some continuity errors with newly added or re-edited sections. 

Nothing in particular textbook. 

If you need to some introductive reference books, "The Hundred-Page Machine Learning Book" is a good. 

During the lecture, I will upload ppt slides and hand out materials accordingly. 

If you would like to study machine learning algorithm in more depth, I recommend following books:

• Machine Learning: An Algorithmic Perspective, Second Edition, Stephen Marsland, Chapman and Hall/CRC; 2 edition (October 14, 2014) 

• Introduction to Machine Learning (Adaptive Computation and Machine Learning series), Ethem Alpaydin, The MIT Press; forth edition (March 24, 2020) 

• Machine Learning: A Probabilistic Perspective (Adaptive Computation and Machine Learning series), Kevin P. Murphy, The MIT Press; 1 edition (August 24, 2012)

There will be a quiz in each lecture(Not always). The quiz scores account for 40% of the total grade. The deadline for submissions is 24:00 on the following Monday.

I will submit three reports in the whole lecture. The grade of the report is 60% of the total grade. All reports are due at the end of January next year, but I recommend you are encouraged to start them immediately after the assignment.

Since some students are undergraduates, I ask you to submit their papers from a special page( not via LMS).

All ansewers of quizes and reports must be submitted in pdf format. Do not forget your student ID number and name. Every year, there are reports from unknown submitter(s).

If you have any questions, please contact me by email.

The following topics are  tentative, and slightly different from those in the syllabus, but the content remains largely unchanged. The schedule may be be changed. 

0 Introduction 2023/10/17 

1  Linear Problem(regression, discriminant)   2023/10/17

2 Perceptron    

3 Neural Networks  

4 Report (1)     🍂

5 Support vector machine (SVM)    

6 Decision tree    

7 Ensemble learning   

8 Clustering   

9 Report(2)    🎄

10 Self Organizing Map  🎍

11 Reinforcement learning  

12  Deep learning and its application

13  Transformer

14 Generative model

15 Final report(3)    ⛄