| Instructor | Julian McAuley |
| Room | Warren Lecture Hall (WLH) 2001 |
| Days & times | 9:30-10:50am, Tuesdays & Thursdays |
| Office hours | posted on Piazza |
[piazza] [gradescope] [twitch]
CSE 153 and 253 (and 153R / 253R) are undergraduate and graduate courses devoted to the application of machine learning to understand and generate music. After taking this course, students will be able to understand and manipulate data (and data structures) for music representation; students will be able to build predictive models and pipelines for music information retrieval; and students will be able to algorithmically synthesize music, culminating in a project demonstrating their creative work.
No previous background in machine learning or music is required, but all participants should be comfortable with programming (all example code will be in Python), and with basic optimization and linear algebra.
Under construction! All materials should be regarded as drafts until they are presented
| module | week (approx) | slides | workbook | |
|---|---|---|---|---|
| course introduction | ||||
| 1 | 1-2 | data structures for music and data ingestion | workbook 1 | |
| 2 | 3-4 | simple predictive pipelines for music | ||
| 3 | 5-6 | symbolic-domain music generation | ||
| 4 | 7-8 | continuous-domain music generation | ||
| 5 | 9 | other topics in Music ML | ||
| 10 | musical performances! |
| Homework | 50% | Assignments | 50% |
|---|---|---|---|
| ├ Homework 1 | 10% | ├ Assignment 1 | 25% |
| ├ Homework 2 | 10% | ├ Assignment 2 | 25% |
| ├ Homework 3 | 10% | ||
| ├ Homework 4 | 10% | ||
| ├ Homework 5 | 10% |