yongxie-icmm / mece4520

Materials for the course: Data Science for Mechanical System

Data Science for Mechanical Systems

Last update: 2021-09-05.

This repo contains the materials for the course "MECE 4520: Data Science for Mechanical Systems", offered by the Department of Mechanical Engineering at Columbia University, during the Fall 2021 term. Link on Directory of Classes.

Objective

This course aims to provide the students a general introduction of data science and machine learning, with hands-on exercises and applications in mechanical system. The main topics to cover includes supervised learning problems, such as linear regressions and classifications; unsupervised learning problems such as clustering; and reinforcement learning problems. At the end of the course, the students should be equipped with basic concepts data science, and comfortable of applying them to practical problems.

Time and location

• Lectures: Tuesday 1:10 PM ~ 3:40 PM.
• Location Ren Kraft Center.
• Office Hours: TBD.

Staffs

• Lecturer: Changyao Chen ([email protected])
• TA: Xin Meng ([email protected])

Prerequisites

Linear algebra. Knowledge of basic computer programming (e.g., Python, Matlab, R, Java).

Course format and grading policy

The course will delivered as a series of 2.5-hour long lectures. The grading will be 60% homework, and 40% final project. There will be in total 4 homework (HW) assignments, which are due throughout the course. The final project will be a group-based, 5-minute presentation of a selected topic (details TBD).

Syllabus

Date	Topic(s)	Optional Readings	Due that day
2021-09-14	Lecture 1: Introduction and linear algebra.
2021-09-21	Lecture 2: Statistic primer.
2021-09-28	Lecture 3: Linear regression.		HW #1
2021-10-05	Lecture 4: Classification and logistic regression.
2021-10-12	Lecture 5: Feature selection, regularization.		HW #2
2021-10-19	Lecture 6: (Mid-term week) Dimension reduction.
2021-10-26	Lecture 7: Tree-based models.
2021-11-02	No class (Election Day, University Holiday).		HW #3
2021-11-09	Lecture 8: Neural Networks.		Final project selection
2021-11-16	Lecture 9: Unsupervised learning and reinforcement learning.
2021-11-23	Lecture 10: (Thanksgiving week) Dynamical system.
2021-11-30	Final project presentations, part I.		HW #4
2021-12-07	Final project presentations, part II.

* DDSE is short for Data-Driven Science and Engineering

Reference

Text book:

• Data-Driven Science and Engineering (link)

Data science

• An Introduction to Statistical Learning (link)
• The Elements of Statistical Learning (link)
• Python for Data Analysis (link)
• Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (link)

Python and general programming

• Python Crash Course (link)
• Real Python (link)
• The Linux Command Line (link)