國立中興大學教學大綱

課程名稱	(中) 深度學習(4269)
	(Eng.) Deep learning
開課單位	電資學士
課程類別	選修			學分	3	授課教師	劉宗榮
選課單位	電資學士 / 學士班			授課使用語言	中/英文	英文/EMI		開課學期	1121
課程簡述	This course will allow students to understand data representation and mathematical models in-depth while cultivating their skills in translating mathematical thinking into practical code. Moreover, by learning the fundamentals and recent advancements in deep learning, students will be able to apply deep learning techniques to solve complex real-world problems with the expectation that they can contribute to the development of artificial intelligence.
先修課程名稱								課程含自主學習	N

課程與核心能力關聯配比(%)			課程目標之教學方法與評量方法
課程目標	核心能力	配比(%)	教學方法	評量方法
This course is concerned with the following objectives: • Understanding data representation and underlying mathematical formulas for deep learning: We will delve into various data representations, such as vectors, matrices, tensors, etc., and explore the mathematical principles and applications behind these representations. • Translating mathematical formulas of deep learning into code: We will learn how to transform mathematical formulas into code to achieve specific tasks. It involves selecting appropriate models and writing efficient and reliable code. Additionally, we will learn how to evaluate and interpret the results to verify their correctness and effectiveness. • Learning the fundamentals and recent advancements in deep learning: Deep learning is a significant branch of artificial intelligence that emulates the structure and functionality of the human brain, enabling automatic learning and extraction of critical features from data. This course will teach students basic deep learning concepts, including various neural networks, forward/backward propagations, etc. We will also explore the latest developments in deep learning, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and generative adversarial networks (GANs), and understand their applications in image processing.			專題探討/製作 習作 討論 講授	書面報告 出席狀況 口頭報告 作業
授課內容(單元名稱與內容、習作/每週授課、考試進度-共18週)
週次 授課內容 第1週 Basic introduction to artificial intelligence (Chap 1) 第2週 Introduction to Environmental and Data Science Packages (Chap 2) 第3週 Introduction to Environmental and Data Science Packages (Chap 2) 第4週 Introduction to Environmental and Data Science Packages (Chap 2) 第5週 Machine Learning and Deep Learning Fundamentals (Chap 3) 第6週 Machine Learning and Deep Learning Fundamentals (Chap 3) 第7週 Machine Learning and Deep Learning Fundamentals (Chap 3) 第8週 Neural Networks and Convolutional Neural Networks (Chap 4) 第9週 Neural Networks and Convolutional Neural Networks (Chap 4)/ HW #1 第10週 Common Deep Learning Training Techniques (Chap 5) 第11週 Introduction to Deep Learning Architectures (Chap 6) 第12週 Advanced Deep Learning Techniques (Chap 7)/ HW #2 第13週 Advanced Deep Learning Techniques (Chap 7)/ HW #3 第14週 Some Deep Learning Examples for image processing (Chap 8) 第15週 Some Deep Learning Examples for image processing (Chap 8)/ HW #4 第16週 Some Deep Learning Examples for image processing (Chap 8) 第17週 Term Project 第18週 Term Project
學習評量方式
Homework: 40% Term Project: 50% Attendance: 10%
教科書＆參考書目(書名、作者、書局、代理商、說明)
Textbook 彭彥璁,李偉華,陳彥蓉, “深度學習–影像處理應用”, 初版, 全華圖書, 2023 Reference book Sebastian Raschka, Yuxi (Hayden) Liu, and Vahid Mirjalili, “Machine Learning with PyTorch and Scikit-Learn”, 1st edition, Packt Publishing, 2022.
課程教材（教師個人網址請列在本校內之網址）
iLearning 3.0
課程輔導時間
Thursday 5:00pm – 6:00pm or by appointment
聯合國全球永續發展目標
09.工業、創新基礎建設 提供體驗課程：N

請尊重智慧財產權及性別平等意識，不得非法影印他人著作。
更新日期 西元年/月/日：2023/09/09 12:58:03	列印日期 西元年/月/日：2024 / 5 / 09
MyTB教科書訂購平台：http://www.mytb.com.tw/