6.390 Intro to
Machine Learning
Course Structural Overview
Shen Shen
December 9, 2022
Syllabus
Info/prereqs
Course Pedagogy
A nominal week: mix of theory, concepts, and application to problems!
Grading: Exercises: 5%, Attendance: 5%, Homeworks: 15%,Lab Checkoff: 15%, Midterm: 25%, Final: 35%
- Reading Notes: all the "facts" and "points" we expect
- Exercises: easy questions based on notes (and optional viewing of previous recorded lecture)
- Recitation: In-class pen/paper problems; assumes you have read and done exercises; start on homework
- Homework: (9-days) Harder questions: concepts, mechanics, implementations
- Lab: In-class empirical exploration of concepts; work with partner on lab assignment; Check-off conversation with staff member
- Office hours (18 hours) and Piazza help
Student Body
Some Policy "Quirks"
- Infinite submissions
- No sick attendence
- 20-day auto extensions
Staff/management
Vision/Evolution
Kick-off point ML family tree
What's brewing
- Course materials by topic (meta tags)
- Collaborative notes-reading
- inspired by Russ's hypothesis plugin https://underactuated.mit.edu/pend.html
- One week dedicated to "what's trendy/latest"?
- Resources Sharing
- Problems bank; tags/filters
- Piazza FAQs bank
- Staff handbooks
- Centralized personnel db (e.g. we benefitted from joint LA hiring)
6.390 overview
By Shen Shen
6.390 overview
- 107