2024 Faculty Courses School of Computing Department of Mathematical and Computing Science Graduate major in Artificial Intelligence
Image and Video Recognition
- Academic unit or major
- Graduate major in Artificial Intelligence
- Instructor(s)
- Nakamasa Inoue
- Class Format
- Lecture (HyFlex)
- Media-enhanced courses
- -
- Day of week/Period
(Classrooms) - 1-2 Mon / 1-2 Thu
- Class
- -
- Course Code
- ART.T551
- Number of credits
- 200
- Course offered
- 2024
- Offered quarter
- 4Q
- Syllabus updated
- Mar 14, 2025
- Language
- English
Syllabus
Course overview and goals
This course gives an overview of the foundational ideas with some recent advances in image and video recognition. It covers deep neural networks such as convolutional neural networks, region proposal networks, fully convolutional networks and generative adversarial networks. Through lectures and assignments, students will learn the necessary skills to implement their own neural networks.
Course description and aims
At the end of this course, students should be able to
1) explain the basic concepts of image and video recognition, and
2) implement their own network by using deep learning libraries
Keywords
Deep Learning, Neural Networks, Image Recognition, Video Recognition
Competencies
- Specialist skills
- Intercultural skills
- Communication skills
- Critical thinking skills
- Practical and/or problem-solving skills
Class flow
This course will be taught with slides.
Course schedule/Objectives
| Course schedule | Objectives | |
|---|---|---|
| Class 1 | Introduction |
Overview of current image and video recognition technologies. |
| Class 2 | Basics for deep learning |
Fundamentals of linear algebra and deep learning. |
| Class 3 | Tools for Deep Learning |
Fundamentals of deep learning implementation. |
| Class 4 | Image Classification |
Convolutional neural networks. |
| Class 5 | Loss and optimization |
Region proposal networks. |
| Class 6 | Object Detection |
Region proposal networks. |
| Class 7 | Exercise for Object Detection |
Implementation of object detection models. |
| Class 8 | Image Segmentation |
Fully convolutional networks |
| Class 9 | Action Recognition |
Action Recognition |
| Class 10 | Image Generation |
Generative adversarial networks. |
| Class 11 | Exercise for Image Generation |
Implementation of image generation models. |
| Class 12 | Comprehensive Exercise |
Comprehensive implementation of deep learning models. |
| Class 13 | Student workshop 1 |
Present and discuss the results of exercises and the final report. |
| Class 14 | Student workshop 2 |
Present and discuss the results of exercises and the final report. |
Study advice (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)
-
Reference books, course materials, etc.
I. Goodfellow, Y. Benito, A. Courville, Deep Learning, MIT Press, 2016.
D. Foster, Generative Deep Learning, O'Reilly Media, 2019.
Evaluation methods and criteria
Assignments (100%)
Related courses
- ART.T458 ： Advanced Machine Learning
- XCO.T489 ： Fundamentals of artificial intelligence
- XCO.T490 ： Exercises in fundamentals of artificial intelligence
- XCO.T483 ： Advanced Artificial Intelligence and Data Science A
- XCO.T485 ： Advanced Artificial Intelligence and Data Science C
- XCO.T486 ： Advanced Artificial Intelligence and Data Science D
Prerequisites
-