Information
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 of course programming experience can be helpful). If you have any questions or suggestions on the course please feel free to contact me.
Materials
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:
This course can not be used to get credits for graduation in any program at Nagoya University, but still, students can obtain a final grade that can show up in their final transcript. This grade will be based on submitted homework assignments, which will be a mix of programming and math exercises. Please sign up for the NUCT course if you want to submit homework.
Course schedule (tentative)
Lecture:
The following gives a tentative overview of the topics we will cover each week.
Week 01 (10/03-10/09): Introduction to machine learning and Python
Week 02 (10/10-10/16): No lecture (体育の日, Sports day: Please do 100 pushups instead), but there will be a Tutorial.
Week 03 (10/17-10/24): Linear regression & Gradient descent
Week 04 (10/24-10/30): Logistic regression & Maximum likelihood
Week 05 (10/31-11/06): Homework 2
Week 06 (11/07-11/13): Classes in Python
Week 07 (11/14-11/20): Naive Bayes I
Week 08 (11/21-11/27): Naive Bayes II & Homework 3 & Gaussian Discriminant Analysis
Week 09 (11/28-12/04): skipped
Week 10 (12/04-12/11): Unsupervised learning: K-means
Week 11 (12/11-12/18): Reinforcement learning: Q-learning
Week 12 (12/19-12/25): Reinforcement learning: Q-learning II & Homework 4
Winter Vacation (12/28-01/07) 🎅🎄☃️ (No lecture on December 26th 2022)
Week 13 (01/09-01/15): Coming-of-age Day (No lecture on January 9th 2023)
Week 14 (01/16-01/22): Neural Networks I
Week 15 (01/23-01/29): Neural Networks II
Week 16 (01/30-02/06): Neural Networks III & Examples in TensorFlow
Last update: 30th January 2023.
- If you are Japanese student, please also register at the NU-EMI project for this course.
- Please join the NUCT Course for this class. We will use NUCT for the homework submission.
- We will use a Discord server for communication and for sharing materials & code.
- This course is a "Special Mathematics Lecture", which is an optional subject. It does not count towards the number of credits required for graduation in any program at Nagoya University. But students can get a grade for this course which can show up in their final transcript.
- Registration Code: 0061621
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 of course programming experience can be helpful). If you have any questions or suggestions on the course please feel free to contact me.
Materials
- Lecture notes: Version 6 (23rd January 2023)
- Lecture slides (without annotation): Lecture 1, Lecture 2, Lecture 3, Lecture 6, Lecture 7, Lecture 8, Lecture 9, Lecture 10, Lecture 11, Lecture 12, Lecture 13
- Lecture slides (with annotation): Lecture 2, Lecture 3, Lecture 6, Lecture 9, Lecture 12
- Lecture Colab Notebooks: Lecture 1, Lecture 2, Lecture 3, Lecture 5, Lecture 7, Lecture 8, Lecture 9, Lecture 11, Lecture 13
- Tutorial Colab Notebooks: Tutorial 1, Tutorial 3, Tutorial 9
- Homework: Homework 1, Homework 2, Homework 3, Homework 4
- NU Connect competition
- The Fall 2020 version of this course (online)
- Andrew Ng: CS229 Lecture Notes (Based on a course given in Fall2022 at Stanford. This covers much more than we will be able to do in our course, but it can serve as a good reference for students who want to self study)
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 programming in Python
- Overview of machine learning
- Supervised learning: Linear & logistic regression
- Generative Learning algorithms: Naive Bayes
- Reinforcement Learning: Q-Learning
- Unsupervised learning: k-means clustering
- Neural networks & Deep learning
This course can not be used to get credits for graduation in any program at Nagoya University, but still, students can obtain a final grade that can show up in their final transcript. This grade will be based on submitted homework assignments, which will be a mix of programming and math exercises. Please sign up for the NUCT course if you want to submit homework.
Course schedule (tentative)
Lecture:
- Time: Monday 6th period (18:15-19:45)
- First Lecture on Monday 3rd October 2022
- Room: A250, 2nd floor, Science A building (Computer room)
- Time: Thursday 6th period (18:15 - 19:45)
- First Tutorial on Thursday 6th October 2022
- Room: A250, 2nd floor, Science A building (Computer room)
The following gives a tentative overview of the topics we will cover each week.
Week 01 (10/03-10/09): Introduction to machine learning and Python
Week 02 (10/10-10/16): No lecture (体育の日, Sports day: Please do 100 pushups instead), but there will be a Tutorial.
Week 03 (10/17-10/24): Linear regression & Gradient descent
Week 04 (10/24-10/30): Logistic regression & Maximum likelihood
Week 05 (10/31-11/06): Homework 2
Week 06 (11/07-11/13): Classes in Python
Week 07 (11/14-11/20): Naive Bayes I
Week 08 (11/21-11/27): Naive Bayes II & Homework 3 & Gaussian Discriminant Analysis
Week 09 (11/28-12/04): skipped
Week 10 (12/04-12/11): Unsupervised learning: K-means
Week 11 (12/11-12/18): Reinforcement learning: Q-learning
Week 12 (12/19-12/25): Reinforcement learning: Q-learning II & Homework 4
Winter Vacation (12/28-01/07) 🎅🎄☃️ (No lecture on December 26th 2022)
Week 13 (01/09-01/15): Coming-of-age Day (No lecture on January 9th 2023)
Week 14 (01/16-01/22): Neural Networks I
Week 15 (01/23-01/29): Neural Networks II
Week 16 (01/30-02/06): Neural Networks III & Examples in TensorFlow
Last update: 30th January 2023.