Print

2022　Image and Video Recognition

Font size  SML

Register update notification mail Add to favorite lecture list
Academic unit or major
Graduate major in Artificial Intelligence
Instructor(s)
Inoue Nakamasa 
Class Format
Lecture    (HyFlex)
Media-enhanced courses
Day/Period(Room No.)
Mon1-2(H105)  Thr1-2(H105)  
Group
-
Course number
ART.T551
Credits
2
Academic year
2022
Offered quarter
4Q
Syllabus updated
2022/4/20
Lecture notes updated
-
Language used
English
Access Index

Course description and aims

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.

Student learning outcomes

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 that will be developed

✔ 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/Required learning

  Course schedule Required learning
Class 1 Introduction Overview of image and video recognition
Class 2 Basic Mathematics for Deep Learning Linear algebra and optimization
Class 3 Tools for Deep Learning Python libraries for deep learning
Class 4 Image Classification Convolutional neural networks
Class 5 Object Detection Region proposal networks
Class 6 Image Segmentation Fully convolutional networks
Class 7 Action Recognition
Class 8 Data Augmentation Data augmentation for image recognition
Class 9 Image Generation Generative adversarial networks
Class 10 Adversarial Examples Adversarial examples and defense methods
Class 11 Domain Adaptation Adaptation and transfer learning methods
Class 12 Zero-Shot Learning Zero-shot learning methods using attributes and texts
Class 13 Distributed Learning Learning with multiple GPUs
Class 14 Theoretical Analysis of Deep Learning Theoretical Analysis of Deep Learning

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)

-

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.

Assessment criteria and methods

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

-

Page Top