▶Japanese
Post to SNS
- Academic unit or major
- Center of Data Science and Artificial Intelligence
- Instructor(s)
- Ono Isao Inoue Nakamasa Yamada Hiroaki Nitta Katsumi Miyake Yoshihiro
- Class Format
- Lecture (Livestream)
- Media-enhanced courses
- Day/Period(Room No.)
- Wed5-6()
- Group
- -
- Course number
- DSA.A601
- Credits
- 1
- Academic year
- 2023
- Offered quarter
- 4Q
- Syllabus updated
- 2023/9/27
- Lecture notes updated
- -
- Language used
- English
- Access Index
-
Course description and aims
Deep learning is one of the artificial intelligence techniques using multi-layer neural networks, and has produced significant results in various fields such as image recognition, speech recognition, and natural language processing. In this course, we teach representative deep learning methods and their applications, which are important for researchers and engineers in science and engineering fields. The course deals with advanced topics that are not covered in the courses of Fundamentals of Artificial Intelligence and Fundamentals of progressive Artificial Intelligence.
Student learning outcomes
The goal is to understand typical algorithms of deep learning and their applications.
Keywords
Deep learning，CNN，VAE，GAN，RNN，LSTM，Attention，Transformer，Deep reinforcement learning
Competencies that will be developed
| ✔ Specialist skills | Intercultural skills | Communication skills | Critical thinking skills | Practical and/or problem-solving skills |
Class flow
ZOOM is used to allow students to take courses at Ookayama or Suzukakedai campuses.
Course schedule/Required learning
| Course schedule | Required learning | |
|---|---|---|
| Class 1 | CNN, VAE, GAN and their applications to speech and image recognition (1) | Understanding CNN, VAE, GAN and their applications to speech and image recognition. |
| Class 2 | CNN, VAE, GAN and their applications to speech and image recognition (2) | Understanding CNN, VAE, GAN and their applications to speech and image recognition. |
| Class 3 | RNN, LSTM, Attention, Transformer and their applications to natural language processing and speech recognition (1) | Understanding RNN, LSTM, Attention, Transformer and their applications to natural language processing and speech recognition. |
| Class 4 | RNN, LSTM, Attention, Transformer and their applications to natural language processing and speech recognition (2) | Understanding RNN, LSTM, Attention, Transformer and their applications to natural language processing and speech recognition. |
| Class 5 | Deep Reinforcement Learning and Its Applications to Robot Control and Natural Language Processing (1) | Understanding deep reinforcement learning and its applications to robot control and natural language processing. |
| Class 6 | Deep Reinforcement Learning and Its Applications to Robot Control and Natural Language Processing (2) | Understanding deep reinforcement learning and its applications to robot control and natural language processing. |
| Class 7 | Deep Reinforcement Learning and Its Applications to Robot Control and Natural Language Processing (3) | Understanding deep reinforcement learning and its applications to robot control and natural language processing. |
Out-of-Class Study Time (Preparation and Review)
To enhance effective learning, students are encouraged to spend approximately 100 minutes preparing for class and another 100 minutes reviewing class content afterwards (including assignments) for each class.
They should do so by referring to textbooks and other course material.
Textbook(s)
None
Reference books, course materials, etc.
Distributed electronically at T2SCHOLA.
Assessment criteria and methods
Evaluation is based on in-class assignments and reports, and advanced assignment reports.
Related courses
- Fundamentals of progressive data science（XCO.T677）
- Exercises in fundamentals of progressive data science（XCO.T678）
- Fundamentals of progressive artificial intelligence（XCO.T679）
- Exercises in fundamentals of progressive artificial intelligence（XCO.T680）
Prerequisites (i.e., required knowledge, skills, courses, etc.)
- Students should have basic knowledge of linear algebra, differential and integral calculus, and mathematical statistics.
- Students should have basic programming skills in Python.
- Students should be able to understand the content taught in Fundamentals of Artificial Intelligence or Fundamentals of Progressive Artificial Intelligence, as well as in Exercises in Fundamentals of Artificial Intelligence or Exercises in Fundamentals of Progressive Artificial Intelligence.
