2023 Faculty Courses School of Engineering Undergraduate major in Electrical and Electronic Engineering
Electrical and Electronic Informatics II
- Academic unit or major
- Undergraduate major in Electrical and Electronic Engineering
- Instructor(s)
- Tomohiro Amemiya / Keigo Arai
- Class Format
- Lecture (Face-to-face)
- Media-enhanced courses
- -
- Day of week/Period
(Classrooms) - 7-8 Tue (S2-204(S221)) / 7-8 Fri (S2-204(S221))
- Class
- -
- Course Code
- EEE.M252
- Number of credits
- 200
- Course offered
- 2023
- Offered quarter
- 4Q
- Syllabus updated
- Jul 8, 2025
- Language
- Japanese
Syllabus
Course overview and goals
In addition to the machine learning methods learned in "EEE.M251: Electrical and Electronic Informatics I", this course (EEE.M252) covers various algorithms for deep learning. An understanding of the basic concepts of deep learning is important for future research and development in various fields of electrical and electronic systems.
Course description and aims
Students will acquire the following abilities.
1) Deepen understanding of various algorithms for deep learning.
2) To be able to code a simple neural network in Python.
Keywords
AI, deep learning, Python
Competencies
- Specialist skills
- Intercultural skills
- Communication skills
- Critical thinking skills
- Practical and/or problem-solving skills
- Applied professional capacity in electrical and electronic fields
Class flow
In each lecture, explanations will be given using slide materials uploaded to T2SCHOLA. In addition, four exercises will be conducted.
Course schedule/Objectives
| Course schedule | Objectives | |
|---|---|---|
| Class 1 | Fundamentals of neural networks | Deepen understanding of the overall overview of deep learn |
| Class 2 | Backpropagation and vanishing gradient problem | Learn about training algorithms in neural networks |
| Class 3 | Various technologies for deep neural networks | Learn about typical convergence methods used for deep networks |
| Class 4 | Convolutional neural networks (CNN) 1 | Learn the basics of convolutional neural networks (CNN) for image data processing |
| Class 5 | Convolutional neural networks (CNN) 2 | Learn the basics of convolutional neural networks (CNN) for image data processing |
| Class 6 | ＜Exercise＞ Implementing a CNN in Python 1 | Implementing a CNN in Python |
| Class 7 | ＜Exercise＞ Implementing a CNN in Python 2 | Implementing a CNN in Python |
| Class 8 | Recursive neural networks (RNNs) | Learn about recursive neural networks for time series data processing |
| Class 9 | Attention mechanism and Transformer 1 | Explain the details of the Attention Mechanism and Transformer. |
| Class 10 | Attention mechanism and Transformer 2 | Explain the details of the Attention Mechanism and Transformer. |
| Class 11 | ＜Exercise＞ Implementing attention mechanism in Python 1 | Implementing attention mechanism in Python |
| Class 12 | ＜Exercise＞ Implementing attention mechanism in Python 2 | Implementing attention mechanism in Python |
| Class 13 | Generative adversarial network (GAN) and variational auto-encoder (VAE) | Learn about generative adversarial network (GAN) and variational auto-encoder (VAE) |
| Class 14 | Diffusion Model 1 | Learn about new developments in data generation technology |
| Class 15 | Diffusion Model 2 | Learn about new developments in data generation technology |
Study advice (preparation and review)
Basically, no preparation for the class is required, but it is strongly recommended to read through the relevant sections of reference books to deepen your understanding based on the outline explained in class.
Textbook(s)
Nothing in particular, but I strongly recommend ’Fire Salamander’, the first reference book.
Reference books, course materials, etc.
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (O'Reilly)
Natural Language Processing With Transformers: Building Language Applications With Hugging Face (O'Reilly)
拡散モデル データ生成技術の数理（岩波書店）(in Japanese)
Evaluation methods and criteria
Grades will be assigned as follows.
Attendance report (40%)
Midterm: Submission of Python code (30%)
Final exam (30%)
Related courses
- EEE.M221 ： Computation Algorithms and Programming
- EEE.M231 ： Applied Probability and Statistical Theory
- EEE.M251 ： Electrical and Electronic Informatics I
Prerequisites
EEE.M251 Electrical and Electronic Informatics I : Required
EEE.M221 Computation Algorithms and Programming : Required
EEE.M231 Applied Probability and Statistical Theory : Recommended