I3940 教學大綱表

教學大綱表 (112學年度第2學期)

請遵守智慧財產權，勿使用非法影印教科書，避免觸法。

課程名稱 Course Title	(中文) 深度神經網路實驗 (英文) Deep Neural Network Experiments			開課單位 Departments	資訊工程學系
				課程代碼 Course No.	I3940
授課教師 Instructor	謝禎冏
學分數 Credit	2.0	必/選修 core required/optional	選修	開課年級 Level	大四
先修科目或先備能力(Course Pre-requisites)：程式設計、影像處理
課程概述與目標(Course Overview and Goals)：Deep learning, a branch of machine learning, is the fastest-growing field in artificial intelligence. Deep learning mimics how human neural networks work. This course will teach common deep learning architectures, such as Multilayer Perceptron (Multilayer Perceptron), Deep Neural Network DNN (Deep Neural Network), Convolutional Neural Network CNN (Convolutional Neural Network), Recurrent Neural Network RNN (Recurrent Neural Network). The goal is to enable students to apply deep learning in visual recognition, speech recognition, natural language processing, biomedicine, and other fields and achieve good results. This course is one of the EMI courses taught in English.
教科書(Textbook)	自編
參考教材(Reference)	國際期刊、Python、Keras等相關網站

課程大綱 Syllabus			學生學習目標 Learning Objectives	單元學習活動 Learning Activities	學習成效評量 Evaluation	備註 Notes
序 No.	單元主題 Unit topic	內容綱要 Content summary	學生學習目標 Learning Objectives	單元學習活動 Learning Activities	學習成效評量 Evaluation	備註 Notes
1	Inroduction of Deep Learning	Classic NN	Ex. 1 Sony Neural Network Console(NNC) by logistic regression
2	Convolution	Convolution NN	Ex. 2 LeNet, Mnist 0-9
3	Deeper Learning	Deeper learning	Ex. 3 AlexNet, Cifar-10/100 (Sony/getcifar10.py)
4	Data Set	Prepare Dataset	Ex. 4 Self-made hand gesture dataset(OpenCV)
5	A Real World Application	Hand gesture recognition	Sony NNC / NNL+OpenCV
6	Environment Setup	Install CUDA 10.0, cndnn 10.0, Python, Anaconda, Tensorflow, Keras	Mnist 0-9 and real-time hand gesture recognition
7	Image Annotation Tool	Labelling tool	ImageLabelling/https://github.com/AlexeyAB/Yolo_mark
8	VGG	VGG, Cifar-100/ResNet	Facial expression recognition
9	InceptionNet	InceptionNet	ImageNet
10	Object Detection DNN	Fast/Faster RCNN	Faster RCNN
11	Yolo	Yolo v1~v3	Keras + Yolov3
12	Mask RCNN	Mask RCNN	Mask RCNN
13	Natural Language Processing I	Natural language processing	Positive/Negative comments classification
14	Natural Language processing II	Natural language processing	News classification
15	LSTM	RNN to LSTM	LSTM
16	GAN	Image generation	Image generation
17	Final Exam	Final Exam	Final Exam

彈性教學週活動規劃

序 No.	實施期間 Period	實施方式 Content	教學說明 Teaching instructions	彈性教學評量方式 Evaluation	備註 Notes
1	起:2024-06-11 迄:2024-06-21	5.小專題 Project	實作期末專題	Demo成果與簡報

教學要點概述：
1.自編教材 Handout by Instructor：
■ 1-1.簡報 Slids
□ 1-2.影音教材 Videos
□ 1-3.教具 Teaching Aids
□ 1-4.教科書 Textbook
□ 1-5.其他 Other
□ 2.自編評量工具/量表 Educational Assessment
□ 3.教科書作者提供 Textbook

成績考核 Performance Evaluation：期末考：30% 期中考：30% 專題：10% 彈性教學：10% 作業：20%

教學資源(Teaching Resources)：
□ 教材電子檔(Soft Copy of the Handout or the Textbook)
■ 課程網站(Website)
教學相關配合事項：實驗需在電腦教室進行
課程網站(Website)：網路大學
扣考規定：http://eboard.ttu.edu.tw/ttuwebpost/showcontent-news.php?id=504