Syllabus - HackMD

--- title: Syllabus tags: teach:MF --- # Syllabus ## Agenda 1. [Syllabus](https://hackmd.io/aZyhIpVzSF2BFMJV1RGkhA) 2. [Project](https://hackmd.io/h9Ys2Q-3Szq4mdLh8-t2yg) 3. [ML and FinTech](https://docs.google.com/presentation/d/1EdsotWu_LABvwnFGCzkAolzLWEO-O3Ly/edit?usp=sharing&ouid=109977520360570528980&rtpof=true&sd=true): modified from my previous talk at 交大理律學堂 in February, 2021。 4. Hw1  ## Course materials and Links | App | Note | | ----| ------| | [E3](https://e3new.nctu.edu.tw/login/index.php)|Announcement, homework submission, data, python codes | | [Synchronous online course](https://meet.google.com/xas-xnfm-ckx) | Monday 9:00 - 12:00 | | [Google shared folder](https://drive.google.com/drive/folders/1MtopokfaomSuM0IDe8bduA_GXx7XSb9I?usp=sharing) | earlier videos | | [Google shared folder](https://drive.google.com/drive/folders/16Y6XGv6dr6Hs1-vWTCyLOmiygXtla_4Q?usp=sharing) | videos after 10/25 | | [Jamboard](https://jamboard.google.com/d/19hhdtJykQMCjvyJmdnDvk_MRNJ-RrnYGDFmcl2cYeaI/viewer?f=3)| Scratch | ## Course plan 1. Coordinated by [Prof. Huei-Wen Teng](https://hackmd.io/cxnJOabrRQaLDY7w68_3MA?view) 鄧惠文教授 (交大資財系) will focus on introducing standard supervised and unsupervised learning. Email: venteng@gmail.com 2. One week by [Prof. Fang-Pang Lin 林芳邦教授](https://event.nchc.org.tw/2019/CECEA/index.php?CONTENT_ID=36) (國網中心) on computation acceleration, reinforcement learning, blockchain and bitcoin. 3. Two weeks by [Prof. Henry Horng-Shing Lu](http://misg.stat.nctu.edu.tw/) 盧鴻興教授 (交大統計所) on deep learning neural network. 4. TA: 數據所碩二李亦涵 Email: a0972425933@gmail.com ## Targeted students 1. New to machine learning 2. Interested in FinTech ## Pre-requisites (helpful but not required) 1. Domain knowledge in finance and management 2. Statistics, calculus, linear algebra 3. Python coding ## Grading policy ### 1. Participation and homework (30%) 1. Homework will be assigned mostly weekly base. 2. Students are strongly encouraged to cowork and interact with peers, TA, and instructor. 3. No late homework will be accepted. 4. Homework has to be submitted to E3 for a grade. 5. TA will post homework solutions. ### 2. Exam on 12/20 (35%) 1. In class and open-book 2. If you have university approved conflicts, please inform the instructor one week before the exam in advance to arrange a make-up exam. Otherwise, no make-up exam will be given. ### 3. An individual project (35%) 1. Edit presentation using ppt, google slides, or HackMD. 2. It's fine to have a project as a part of a competition 3. Proposal presentation (11/22) 4. Final presentation (12/27) ## Textbook These textbooks can be freely downloaded through NYCU library. 1. [JWHT] abbreviates for, [James, Witten, Hastie, Tibshirani (2013) An Introduction to Statistical Learning with applications in R. Springer](https://link.springer.com/book/10.1007/978-1-4614-7138-7?gclid=CjwKCAjwzt6LBhBeEiwAbPGOgSRGZonyMkKdIiG7VVRDGguC6f8rHUHDUvU43RGWiJ4RxuVNhy4e9BoCjUkQAvD_BwE). 2. [Course slides in Github](https://github.com/khanhnamle1994/statistical-learning) ## Other reference 1. [Hastie, Tibshirani, and Freidman (2009) The Elements of Statistical Learning. Springer](https://link.springer.com/book/10.1007/978-0-387-84858-7) ### Statistics oriented 1. [Penn State, STAT508](https://online.stat.psu.edu/stat508/) ### CS oriented 1. [MIT, Introduction to Machine Learning, Spring 2016.](https://people.csail.mit.edu/dsontag/courses/ml16/) 2. [Stanford, CS229](http://cs229.stanford.edu/) ## Hw 1 *After a second thought, I give you an extention of one week more for the due date of homeowork 1.* You will do an individual final project. The final project will include: Motivations, Problem formulation, Data description, Analysis, and Conclusion. To prepare the project, in homework 1, think about "Motivations and Why" and write down your answers using *HackMD*, *ppt*, or *google slides*. In this homework, please write down: (1) Motivations and Why (2) the link of your project (3) keywords. Finally, submit your slides in pdf to e3.