Course Syllabus

Course Information：

Year-Semester Course Number Course Name Phase Credits Hours Required/Elective Instructor Class Student NO. Withdraw Note

Fall Semester
Year 2020 280299 Building Deep Learning Applications 1 3.0 3 ★ Kuan-Ting Lai ECE
IEECSG 89 2 ◎

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Fall Semester Year 2020	280299	Building Deep Learning Applications	1	3.0	3	★	Kuan-Ting Lai	ECE IEECSG	89	2	◎

Course Plan：

Instructor Kuan-Ting Lai

Email ktlai@ntut.edu.tw

Last Updated 2020-06-10 14:23:20

Course Objective The goal of this course is to give students a broad overview of state-of-the-art deep learning algorithms, and teach students how to develop deep learning applications by hands-on coding examples. Most examples taught in this class are based on the TensorFlow framework. We will cover many different fields including image classification, object detection, natural language processing, reinforcement learning, embedded deep learning and generative adversarial networks. The syllabus is listed as follows: • Number and Character recognition • Image Classification for 1000 categories • Object Detection for 9000 objects • Convolutional Neural Networks (CNN) • Recurrent Neural Networks (RNN) • Long-Short Term Memory (LSTM) • Generative Adversarial Networks (GAN) • Embedded Deep Learning Algorithms • Deep Reinforcement Learning

Course Schedule
(Week 1-16) 1. Introduction to Deep Learning (Francois (2017), Chapter 1, 2, 3) 2. Applied Math for Machine Learning (Ian et al. (2017), Chapter 2, 3, 4) 3. Fundamentals of Machine Learning (Francois (2017), Chapter 4 + Ian et al. (2017), 5) 4. TensorFlow & Keras + Word Embedding 5. Convolutional Neural Network (CNN) and Image Classification (Francois (2017), Chapter 5) 6. Recurrent Neural Network (RNN) and Long Short-term Memory (LSTM) 7. Object Detection a. YOLO 9000 – You Only Look Once b. Single-shot Multi-Box Detection 8. Generative Adversarial Networks (GAN) 9. Deep Reinforcement Learning a. OpenAI GYM b. Training Autonomous Vehicles in Virtual Reality 10. Virtual Environment for Visual Deep Learning 11. Embedded Deep Learning 12. Student Project Demos

Evaluation and grading policy Homework (50%), Final Project (50%)

Materials All right reserved. Do not reproduce without permission.

Foreign-language textbooks:Yes
Francois Chollet, “Deep Learning with Python, ” Manning, 2017 Ian Goodfellow, Yoshua Bengio, and Aaron Courville, “Deep Learning,” MIT Press, 2017 Latest publications on CVPR, NIPS, ICML, AAAI, ICLR

The access to curricular consultation

Expanding teaching and resources

The course corresponds to the SDGs

Does the course incorporate AI

Note
　

Instructor	Kuan-Ting Lai
Email	ktlai@ntut.edu.tw
Last Updated	2020-06-10 14:23:20
Course Objective	The goal of this course is to give students a broad overview of state-of-the-art deep learning algorithms, and teach students how to develop deep learning applications by hands-on coding examples. Most examples taught in this class are based on the TensorFlow framework. We will cover many different fields including image classification, object detection, natural language processing, reinforcement learning, embedded deep learning and generative adversarial networks. The syllabus is listed as follows: • Number and Character recognition • Image Classification for 1000 categories • Object Detection for 9000 objects • Convolutional Neural Networks (CNN) • Recurrent Neural Networks (RNN) • Long-Short Term Memory (LSTM) • Generative Adversarial Networks (GAN) • Embedded Deep Learning Algorithms • Deep Reinforcement Learning
Course Schedule (Week 1-16)	1. Introduction to Deep Learning (Francois (2017), Chapter 1, 2, 3) 2. Applied Math for Machine Learning (Ian et al. (2017), Chapter 2, 3, 4) 3. Fundamentals of Machine Learning (Francois (2017), Chapter 4 + Ian et al. (2017), 5) 4. TensorFlow & Keras + Word Embedding 5. Convolutional Neural Network (CNN) and Image Classification (Francois (2017), Chapter 5) 6. Recurrent Neural Network (RNN) and Long Short-term Memory (LSTM) 7. Object Detection a. YOLO 9000 – You Only Look Once b. Single-shot Multi-Box Detection 8. Generative Adversarial Networks (GAN) 9. Deep Reinforcement Learning a. OpenAI GYM b. Training Autonomous Vehicles in Virtual Reality 10. Virtual Environment for Visual Deep Learning 11. Embedded Deep Learning 12. Student Project Demos
Evaluation and grading policy	Homework (50%), Final Project (50%)
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:Yes Francois Chollet, “Deep Learning with Python, ” Manning, 2017 Ian Goodfellow, Yoshua Bengio, and Aaron Courville, “Deep Learning,” MIT Press, 2017 Latest publications on CVPR, NIPS, ICML, AAAI, ICLR
The access to curricular consultation
Expanding teaching and resources
The course corresponds to the SDGs
Does the course incorporate AI
Note