Type of Credit: Elective
Credit(s)
Number of Students
能力項目說明
The objective of this class includes understanding data representation and underlying mathematical formulation, as well as turning mathematical formulation into code and understanding/interpreting the results.
| 教學週次Course Week | 彈性補充教學週次Flexible Supplemental Instruction Week | 彈性補充教學類別Flexible Supplemental Instruction Type |
|---|---|---|
Week 1
Subject： Introduction & syllabus
Covering topics: Introduction to Deep Learning.
Reading: N/A
Teaching/HW: Explain the syllabus
Hours spent for preview: N/A
Hours spent for review: 1 hour
--
Week 2
Subject： Mathematical tools
Covering topics: Linear Algebra and Probability
Reading: Course slides
Teaching/HW: Get familiar with math tools often used in machine learning
Hours spent for preview and review: 2 hours each
--
Week 3, 4, 5 (Holiday)
Subject： Machine Learning Basics
Covering topics: linear and logistic regression/classification
Reading: Course slides
Teaching/HW: Introduce various machine learning techniques. HW1 will be released. It needs to be turned in within one week after being released.
Hours spent for preview and review: 2 hours each
--
Week 6
Subject： Optimization and gradient descent
Covering topics: Convex functions and various gradient descent approaches
Reading: Course slides.
Hours spent for preview and review: 2 hours each
Week 7, 8
Subject： Artificial Neural Networks and Deep learning frameworks
Covering topics: Perceptron, Multilayer Perceptron, Back-propagation
Reading: Course slides
Teaching/HW: HW2 will be released. It needs to be turned in within one week after being released.
Hours spent for preview and review: 2 hours each
Week 9
Subject: Midterm Exam
Week 10 & 11
Subject: Convolutional neural networks and training techniques
Covering topics: Convolutional neural networks, often-used architectures and training techniques
Reading: Course slides
Teaching/HW: The final project will be announced
Hours spent for preview and review: 2 hours each
Week 12 & 13
Subject: Recurrent neural networks & Transformers
Covering topics: Recurrent neural networks (RNNs)
Reading: Course slides
Teaching/HW: Teach students RNNs and their underlying math
Hours spent for preview and review: 2 hours each
Week 14 & 15
Subject: Generative AI (Flexible Teaching)
Covering topics: Introduction to generative models, including VAE, GAN, and Diffusion models
Reading: Course slides
Hours spent for preview and review: 2 hours each
Week 16 & 17
Subject: Reinforcement Learning, Large Language Model, Deep Learning Applications (Flexible Teaching)
Covering topics: Policy gradient, Actor-Critic Network, Q Network, Computer vision, and image processing applications
Reading: Course slides
Teaching/HW: Discuss several problems better solved by deep learning
Hours spent for preview and review: 2 hours each
Week 18: Final Presentation
1. Homework (30%) - two homework assignments
2. Midterm Exam (30%)
3. Final Project (40%)
深度學習：影像處理應用，全華圖書 https://www.books.com.tw/products/0010961878?sloc=main Deep Learning https://www.deeplearningbook.org/
1. Neural Network and Deep Learning http://neuralnetworksanddeeplearning.com/ 2. Deep Learning: A Practitioner’s Approach https://www.amazon.com/dp/1491914254?tag=inspiredalgor20