- If you are
**Japanese student,**please also register at the NU-EMI project for this course. - We will use a
**Discord server**for communication and for sharing materials & code. - We will use TACT for homework submission.

****This course is targeted at any student of Nagoya University who is interested in some of the mathematics used in machine learning. As a background I expect that the students have some background in Linear Algebra and Calculus (e.g. Linear Algebra I & Calculus I from the G30 Program). I do not expect that the students can already program, but if you do not have any Python experience you might need to do a basic course by yourself at the beginning (or in the summer break). If you took the Data Science Exercise B then this course is perfect for you. If you have any questions or suggestions on the course please feel free to contact me.

**Materials**

- Lecture notes: Version 5 (27th November 2023)
- Homework: Homework 1, Homework 2, Homework 3, Homework 4
- Google Colab Notebooks: Lecture 1&2, Lecture 3, Lecture 4, Lecture 5, Lecture 6, Lecture 8/9, Lecture 9 (Simple car), Lecture 9 (Advanced Car), Lecture 10, Lecture 11, Lecture 12 (extern), Lecture 13
- Lecture slides: Lecture 1, Lecture 2, Lecture 3, Lecture 4, Lecture 6, Lecture 7, Lecture 8, Lecture 9, Lecture 10, Lecture 11, Lecture 12, Lecture 13
- Links: MNIST CNN Tutorial

**Semester projects**

- here some of the students projects will be displayed -

**Content (tentative)**

Machine learning became a popular and really broad field in recent years. Machine learning algorithms are used in a wide variety of applications, such as email filtering, computer vision, medicine, language translation, computer games, economic, etc.. The goal of this course is to give a brief introduction into machine learning with a focus on the mathematical tools used.

We will probably cover at least the following topics:

- Introduction to machine learning and programming in Python
- Supervised learning: Linear & Logistic regression, Neural networks
- Unsupervised learning: PCA, Autoencoder
- Reinforcement Learning: Q-Learning

**Grading**

The grade will we based on homework submissions and one final project.

The credits follow the

**new rule for SML classes**. (SML=Special mathematics lecture)

Please contact me via email if you have any questions.

**Course schedule**

**(tentative)**

**Lecture**:

- Time: Monday 6th period (18:15-19:45). First lecture: October 2nd.
- Room: A250 (Computer room) in Science Building A (D3 (2) on the Nagoya University Campus map)

**Tutorial:**

- Time: See the calender below (Alternating Thursday (6th period) - Wednesday (5th period) - Friday (6th period) )
- Room: A250 (Same as the lecture)

The following gives a tentative overview of the topics we will cover each week.

Week 01 (10/02-10/08):

****Introduction &

**Linear regression I**

Week 02 (10/09-10/15): No lecture on monday 9th (sports day)

Week 03 (10/16-10/22): Linear regression II

Week 04 (10/23-10/29): Logistic regression

Week 05 (10/30-11/05): Neural Networks I: Basics

Week 06 (11/06-11/12): Neural Networks II: Using tensorflow

Week 07 (11/13-11/19): Neural Networks III: Backpropagation

Week 08 (11/20-11/26): Neural Networks IV: Backpropagation II & Convolutional Neural Networks

Week 09 (11/27-12/03): Reinforcement learning & Q-learning I

Week 10 (12/04-12/10): Q-learning II

Week 11 (12/11-12/17): Deep Q-learning

Week 12 (12/18-12/24): k-means clustering, Christmath Quiz

Week 13 (12/25-12/31):

**🎅**🎄 No Lecture and Tutorial in this week

**🎅**🎄

☃️

**Winter Vacation (12/28-01/09)**☃️

Week 14 (01/08-01/14): No lecture on Monday 8th January (still winter vacation)

Week 15 (01/15-01/21): Principal Component Analysis I

Week 16 (01/22-01/28): Principal Component Analysis II & Autoencoders

Week 17 (01/29-02/06): Semester projects

Last update: 29th January 2024.