課程名稱 |
深度學習於電腦視覺 Deep Learning for Computer Vision |
開課學期 |
106-2 |
授課對象 |
電機資訊學院 電信工程學研究所 |
授課教師 |
王鈺強 |
課號 |
CommE5052 |
課程識別碼 |
942 U0660 |
班次 |
|
學分 |
3.0 |
全/半年 |
半年 |
必/選修 |
選修 |
上課時間 |
星期三2,3,4(9:10~12:10) |
上課地點 |
博理112 |
備註 |
總人數上限:80人 |
Ceiba 課程網頁 |
http://ceiba.ntu.edu.tw/1062DLCV |
課程簡介影片 |
|
核心能力關聯 |
核心能力與課程規劃關聯圖 |
課程大綱
|
為確保您我的權利,請尊重智慧財產權及不得非法影印
|
課程概述 |
Computer Vision has become ubiquitous in our society, with applications in image/video search and understanding, apps, mapping, medicine, drones, and self-driving cars. Core to many of these applications are visual recognition tasks such as image classification, segmentation, localization and detection. Recent developments in neural network (a.k.a. deep learning) approaches have greatly advanced the performance of these state-of-the-art visual recognition systems. This course is a deep dive into details of the deep learning architectures with a focus on learning end-to-end models for solving these tasks. |
課程目標 |
This course will expose students to cutting-edge research — starting from a refresher in basics of machine learning, computer vision, neural networks, to recent developments. The emphasis will be on student-led paper presentations and discussions. Each topic will begin with instructor lectures to present context and background material. |
課程要求 |
Prerequisites: College Calculus, Linear Algebra, Probability, Intro-level Machine Learning |
預期每週課後學習時數 |
|
Office Hours |
|
指定閱讀 |
TBD |
參考書目 |
Deep Learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville
Computer Vision: Algorithms and Applications, Richard Szeliski, 2010 |
評量方式 (僅供參考) |
|
週次 |
日期 |
單元主題 |
第0週 |
3/07 |
Course Logistics + Intro to Computer Vision |
第1週 |
3/14 |
Machine Learning 101 |
第2週 |
3/21 |
Image Representation |
第3週 |
3/28 |
Interest Point: From Recognition to Tracking |
第4週 |
4/04 |
Break; no class |
第5週 |
4/11 |
Intro to Neural Networks + CNN |
第6週 |
4/18 |
Detection & Segmentation |
第7週 |
4/25 |
Generative Models |
第8週 |
5/02 |
Visualization and Understanding NNs |
第9週 |
5/09 |
Recurrent NNs and Seq-to-Seq Models (I) |
第10週 |
5/16 |
Recurrent NNs and Seq-to-Seq Models (II) |
第11週 |
5/23 |
Deep Reinforcement Learning for Visual Applications |
第12週 |
5/30 |
Final Project Announcement + Guest Lecturer (Dr. Yen-Yu Lin) |
第13週 |
6/06 |
Transfer Learning for Visual Analysis |
第14週 |
6/13 |
Learning Beyond Images (2D/3D, depth, etc.) |
第15週 |
6/20 |
Checkpoint for Final Project + Industrial Visit |
第17週 |
07/04 |
Final Project Presentation |
第0-0週 |
2/28 |
Break; no class |
|