用Python於數據科學和機器學習

--Fully online — No in-person meetings required 全線上課程 — 不需到課 --Lectures are recorded and available on YouTube (watch anytime) 課程錄影提供於 YouTube（可隨時觀看） --Every two weeks, you'll work on a group challenge and present your outcome. 每兩週一次小組挑戰，並於課堂中分享成果 --No final exam, no midterm, no homework. 沒有期末考、沒有期中考、沒有作業 --Only 2 hours/week commitment. 每週僅需 2 小時投入 --Each week includes ~20 minutes of lecture; the rest is student presentations. 每週約 20 分鐘講課，其餘時間為學生報告與討論 Course Description This course skips traditional lectures and homework to focus on three things that actually matter when working in machine learning: teamwork, self-learning, and knowing how to use GenAI tools. Every two weeks you'll receive a numerical computing challenge related to machine learning, optimization, matrix factorization, probabilistic modeling, etc. You'll work in a group to solve it, and present your solution in class. The tasks are hard on purpose. You can't complete them alone --> you'll have to rely on your teammates and explore the topic independently. Generative AI tools are encouraged. They're new, evolving, and there's no manual. This course is your chance to understand what they can and can't do. Students usually finish this course with two realizations: --(1) group work is hard --(2) real-world ML is about coding, debugging, and solving problems no one has solved for you. Feel free to check out the playlist from last year--> link: https://youtube.com/playlist?list=PLb1V9aVV3FkHNpORbJzpNM_nciM_RxVnp&si=0IU-Pe-nA0wX89Sm !!IMPORTANT!! Volunteer Opportunity: We need 20% of the class to volunteer as group leaders. They are essential for the success of our collaborative projects, and to encourage participation, we offer a bonus on top of your final grade. If you're interested in volunteering, please DM me on Slack or express your interest on the first day of class.

Basic Python programming → variables, loops, functions, and simple data structures. 基本 Python 程式設計 → 變數、迴圈、函式與基本資料結構。 Basic linear algebra → vectors, matrices, and matrix multiplication. 基本線性代數 → 向量、矩陣與矩陣乘法。 Basic calculus → derivatives and the idea of gradients. 基本微積分 → 導數與梯度的基本概念。 **MOST IMPORTANT** → curiosity and willingness to learn independently. 最重要的是 → 保持好奇心，以及願意自主學習。

無備註

Our teaching methods aim to enhance your learning experience, and we collaborate with the 國立陽明交通大學交大校區教務處教學發展中心 to evaluate class outcomes. We ask that you reflect on the pedagogic objectives and contribute your thoughts on the learning methodologies we employ.

Challenge-based learning framework description https://docs.google.com/document/d/1GA4DIyrkDZwJ0Msq9I4vGjyd3gN6DdntQ_x-L7NBimE/edit?usp=sharing Calendar event with Google Meet link ( Every Wednesday, 13:20 - 14:20 ) Calender Invite : https://calendar.app.google/6odQ7TRpYL71bKMm7 Video call link: https://meet.google.com/vgv-pqmp-arr Slides of the course : https://harvard-iacs.github.io/2021-CS109B/pages/schedule.html Slack channel for the course : https://join.slack.com/share/enQtMTE5NTk5NDA2NDExMjAtMDkxY2VmYWE1NTRjNTQyNDk3MThmMzNkNDBhYTZjMzdlNTQ0Mzc0N2YzMDg5ODM2ZWViNjM3YzFkMTdkNmQwYg "NOTE: If you're unable to join the Slack using the link, kindly drop an email to the TAs" YouTube channel : https://www.youtube.com/@srini2

教師未提供此項資料

Primary reference : Intro to Python for Computer Science and Data Science: Learning to Program with AI, Big Data and The Cloud by Paul J. Deitel and Harvey Deitel Additional recommended readings: --Python Crash Course, 2nd Edition by Eric Matthes --Practice of Computing Using Python, 3rd Edition by William F. Punch and Richard Enbody --Python for Everyone, 2nd Edition by Cay S. Horstmann and Rance D. Necaise --Python for Data Analysis, 2nd Edition by Wes McKinney --Automate the Boring Stuff with Python by Al Sweigart

地點

教師未提供此項資料

時間

教師未提供此項資料

聯絡方式

教師未提供此項資料