Print

2023　Electrical and Electronic Informatics II

Font size  SML

Register update notification mail Add to favorite lecture list
Academic unit or major
Undergraduate major in Electrical and Electronic Engineering
Instructor(s)
Amemiya Tomohiro  Arai Keigo 
Class Format
Lecture    (Face-to-face)
Media-enhanced courses
Day/Period(Room No.)
Tue7-8(S2-204(S221))  Fri7-8(S2-204(S221))  
Group
-
Course number
EEE.M252
Credits
2
Academic year
2023
Offered quarter
4Q
Syllabus updated
2023/8/28
Lecture notes updated
-
Language used
Japanese
Access Index

Course description and aims

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.

Student learning outcomes

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 that will be developed

✔ 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/Required learning

  Course schedule Required learning
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

Out-of-Class Study Time (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)

Assessment criteria and methods

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 (i.e., required knowledge, skills, courses, etc.)

EEE.M251 Electrical and Electronic Informatics I : Required
EEE.M221 Computation Algorithms and Programming : Required
EEE.M231 Applied Probability and Statistical Theory : Recommended

Page Top