Course Syllabus

Course Information：

Year-Semester	Course Number	Course Name	Phase	Credits	Hours	Required/Elective	Instructor	Class	Student NO.	Withdraw	Note
Spring Semester Year 2024	331912	Deep Learning for Digital Image Analysis	1	3.0	3	★	Mohammad	GEE IEECSG	41	3	電機所和電資外生所合開

Course Plan：

Instructor	Mohammad
Email	muhai@ntut.edu.tw
Last Updated	2023-12-15 14:55:47
Course Objective	深度學習數位影像分析，在近代的製造、醫藥、農業、太空探索、運輸和通信系統等應用領域，正迅速發展中。本課程主要介紹深度學習數位影像分析基本理論基礎，以此概念實際應用到各領域中。課程將探索最先進的深度學習模型，如物件偵測、影像分類，和影像分割，提供實用的實務練習；最後討論數位影像分析深度學習的未來挑戰。課程也將介紹最新的公開影像數據集(例如MNIST，CIFAR-10和ImageNet)，並涵蓋用於深度學習中的影像數據前處理和樣本標籤註記，詳細探討深度學習模型的評估指標。本課程將使用Matlab和Python範例，實作教學練習，課程單元包含: ●數位影像分析簡介 ●深度學習基礎 ●影像分析領域之深度學習基本介紹 ●卷積神經網絡 ●訓練卷積神經網絡 ●遷移式學習 ●深度學習數位影像數據標籤註記 ●深度學習模型評估方式 ●深度學習在數位影像分析領域之挑戰 ●超引數優化 ●激活函式 ●損失函式 ●優化函式 This course covers the basics of deep learning for digital image analysis, including theoretical concepts and practical applications. Students will learn about object detection, image classification, and segmentation using state-of-the-art deep learning models. The course will also address the challenges of using deep learning in digital image analysis and cover popular image datasets such as MNIST, CIFAR-10, and ImageNet. Additionally, students will gain hands-on experience in image data preparation and labeling, and learn about evaluation metrics for deep learning models. Programming examples will be provided in Python or Matlab. The course includes: ●A gentle introduction to digital image analysis and deep learning. ●Convolutional neural networks. ●Transfer learning. ●Image data labeling for deep learning. ●Evaluating deep learning models. ●The challenges of deep learning in the field of digital image analysis. ●Activation functions. ●Loss functions. ●Optimizers.
Course Schedule	1. A gentle introduction to digital image analysis. 2. Foundations of deep learning. 3. Deep learning in the field of digital image analysis. 4. Convolutional neural networks. 5. Training convolutional neural networks. 6. Transfer learning. 7. Image data labeling for deep learning. 8. Evaluating deep learning models. 9. The challenges of deep learning in the field of digital image analysis. 10. Hyperparameters. 11. Activation functions. 12. Loss functions. 13. Optimization functions. 14. Final project presentation.
Evaluation and grading policy	Participation (10%) , Assignments (10%), Midterm Test (30%), Final Project (50%) 出席率(10%)、作業(10%)、期中考試(30%)、期末專案(50%)
Materials	All right reserved. Do not reproduce without permission. Foreign-language textbooks:Yes Books: 1- “Digital Image Processing and Analysis: Applications with MATLAB and CVIPtools”, 2017, by Scott E Umbaugh. 2- “Deep Learning”, 2016, by Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 3- “Deep Learning Essentials: Your hands-on guide to the fundamentals of deep learning and neural network modeling”, 2018, by Wei Di, Anurag Bhardwaj, and Jianing Wei. 4- “Artificial Intelligence for Humans, Volume 3: Deep Learning and Neural Networks”, 2015, by Jeff Heaton. Online Books: 1- “Practical MATLAB Deep Learning A Project-Based Approach”, 2020, by Paluszek, Michael, and Thomas, Stephanie. 2- “Deep Learning with Python: A Hands-on Introduction Paperback”, 2017, by Nikhil Ketkar. Selected papers: 1- LeCun, Y., Bengio, Y. and Hinton, G., 2015. Deep learning. nature, 521(7553), pp.436-444. 2- Krizhevsky, A., Sutskever, I. and Hinton, G.E., 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems, 25, pp.1097-1105. 3- Redmon, J. and Farhadi, A., 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767. 4- Badrinarayanan, V., Kendall, A. and Cipolla, R., 2017. Segnet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE transactions on pattern analysis and machine intelligence, 39(12), pp.2481-2495.
The access to curricular consultation	Class.
The course corresponds to the SDGs
Note