AI 研究模組

Unit 1_Mathematics for Machine Learning(馬清文): This course is design to provides on some essential mathematical foundations on which machine learning and artificial intelligence are based. Topics include 1) algebra foundations such as equations, functions, and graphs; 2) differential calculus such as derivatives and optimization; 3) linear algebra such as vector-matrix multiplication and matrix decomposition and; 4) statistics, probability and basic information theory. We will also write python codes to explore the concepts and technologies that are introduced in this course. Unit 2_基礎課程: git, docker, cloud and linux 基礎(魏澤人): 介紹常用軟體開發工具以及相關的概念,包含 * 以 git 為主的版本控制系統, * docker 及虛擬化技術,包含在 windows 上的 ws * 雲端及相關的網路服務概念 * Linux 命令列、 ssh, X 的使用及概念 目的是加速實驗及軟體開發的效率,評量方式以實際操作及心得分享為主。 Unit 3_Deep Learning Hardware and Software(馬清文): Deep learning algorithms require heavy computations. To deal with the demand, judiciously design hardware and software are built. In this course, we will talk about popular software platforms such as Tensorflow/keras and Pytorch. We explore the basic difference between these software platforms and develop the idea of how to choose one from them for our own works. Regarding the deep learning hardware, we will take a look at deep leaning accelerators which are used in edge AI and well-known among many AI chip startups. Unit 4_多旋翼無人機之航拍影像處理(歐陽盟): *數位影像處理 *高光譜智慧偵測 *3D建模

Unit 1_Mathematics for Machine Learning(馬清文): 1.Computer programming skill, especially Python and C. 2.College linear algebra, calculus and probability concepts. 3. In Unit 1, we use Microsoft teams with the link https://tinyurl.com/jhhkuuvh Unit 2_基礎課程: git, docker, cloud and linux 基礎(魏澤人): N/A Unit 3_Deep Learning Hardware and Software(馬清文): 1.Computer programming skill, especially writing Python and C programs. 2.Computer architecture concepts such as CPU, instruction set, memory, data bus, etc. Unit 4_多旋翼無人機之航拍影像處理(歐陽盟): 大學物理、工程數學、程式語言 (Python、C語言、JAVA或其他程式語言之一)

Unit 1_Mathematics for Machine Learning(馬清文): Web resource: 1. Essential math for machine learning https://www.edx.org/course/essential-math-for-machine-learning-python-editi-2 Unit 2_基礎課程: git, docker, cloud and linux 基礎(魏澤人): N/A Unit 3_Deep Learning Hardware and Software(馬清文): 1. Stanford CS231 2020 lecture slides: http://cs231n.stanford.edu/slides/2020/lecture_6.pdf 2. Stanford CS231 2017 Youtube video: Lecture 8 | Deep Learning Software: https://www.youtube.com/watch?v=6SlgtELqOWc&list=PL3FW7Lu3i5JvHM8ljYj-zLfQRF3EO8sYv&index=9&t=0s 3. nVidia Deep learning accelerator: http://nvdla.org/ 4. NVDLA Deep Learning Inference Compiler is Now Open Source: https://devblogs.nvidia.com/nvdla/ Unit 4_多旋翼無人機之航拍影像處理(歐陽盟): N/A

Unit 1_Mathematics for Machine Learning(馬清文): Homeworks: 100% Unit 2_基礎課程: git, docker, cloud and linux 基礎(魏澤人): 教學方式主要為概念講解,現場實際操作,實際演練作業及心得分享 Unit 3_Deep Learning Hardware and Software(馬清文): Homeworks: 100% Unit 4_多旋翼無人機之航拍影像處理(歐陽盟): 3D建模[Implement of 3D Image Construction / 2-3 students]

Unit 1_Mathematics for Machine Learning(馬清文): 1. Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong. MATHEMATICS FOR MACHINE LEARNING. Cambridge University Press, 2020 2. Goodfellow and Yoshua Bengio and Aaron Courville. Deep Learning. Chapter 2,3,4,5. MIT Press, 2016 Unit 2_基礎課程: git, docker, cloud and linux 基礎(魏澤人): N/A Unit 3_Deep Learning Hardware and Software(馬清文): N/A Unit 4_多旋翼無人機之航拍影像處理(歐陽盟):N/A