mirror of
https://github.com/harvard-edge/cs249r_book.git
synced 2026-11-09 10:39:41 -06:00
Vijay Janapa Reddi
945c18aa78
The hub now opens with how the materials fit together, then lists six courses in a fixed order (Introduction, Scaling, Agentic, Physical AI, Edge AI, TinyML), each with an image, its status, what it requires, and links. Every course has a one-page syllabus in one form: a facts table, description, outcomes, and a Week | Topic | Reading | Slides schedule whose Slides column links to the chapter on the separate slides site. Edge AI and Agentic AI gain reading-list pages, and Physical AI moves from a prose guide into the same syllabus form. Draft courses say their materials are still in preparation. The pedagogy, assessment, TA, customization, FAQ, course-map, and setup guides are removed; their URLs redirect to the hub. Grading and lab detail leave the syllabi. The hub and course sites now use the shared site theme with no site-specific styles, so page widths match. The shared theme gains sidebar styles and dark-mode sidebar colors. Course pages share one sidebar and section order, and the course site gains the hub's announcement bar, favicon, and site menu. Writing follows classic expository style, and the README's instructor row matches the hub.
58 lines
3.3 KiB
Plaintext
58 lines
3.3 KiB
Plaintext
---
|
|
title: "TinyML"
|
|
subtitle: "Historical materials · Volume I"
|
|
---
|
|
|
|
## Overview {#overview}
|
|
|
|
Students train models and deploy them on microcontrollers, where limits on
|
|
memory, energy, and latency shape every design choice. This page
|
|
collects the materials from the Harvard CS249r offerings and the HarvardX TinyML
|
|
program. The course assumes Python and basic linear algebra.
|
|
|
|
## Syllabus and schedule {#syllabus}
|
|
|
|
The [TinyML syllabus](https://mlsysbook.ai/instructors/tinyml-syllabus.html)
|
|
pairs each week of the courseware with a Volume I chapter. The syllabi of past
|
|
Harvard offerings appear under [Offerings](#offerings).
|
|
|
|
## Materials {#materials}
|
|
|
|
| Resource | Use |
|
|
|:---|:---|
|
|
| [Lecture slides](https://mlsysbook.ai/slides/tinyml.html) | Decks from the HarvardX TinyML courseware. |
|
|
| [Hardware kits](https://mlsysbook.ai/kits/) | Microcontroller boards and deployment labs. |
|
|
| [Fall 2020 assignments](https://github.com/Harvard-CS249R-Fall2020/assignments) | Starters for hello world, gesture recognition, person detection, wake words, and responsible AI. |
|
|
| [Fall 2022 Assignment 2](https://github.com/mmaz/cs249r-a2) | Visual wake words: training, quantization, and deployment ([Colab](https://colab.research.google.com/github/mmaz/cs249r-a2/blob/master/cs249r_a2.ipynb)). |
|
|
| [TinyMLx courseware](https://github.com/tinyMLx/courseware/tree/master/edX) and [Colabs](https://github.com/tinyMLx/colabs) | Structure, readings, and notebooks from the HarvardX specialization. |
|
|
| [TinyMLx Arduino library](https://github.com/tinyMLx/arduino-library) | Source and examples for the TinyML kit and shield. |
|
|
|
|
## For instructors {#for-instructors}
|
|
|
|
The historical code and hardware instructions have not been rerun on current
|
|
toolchains, so each assignment needs a test run before it is assigned.
|
|
|
|
## Offerings {#offerings}
|
|
|
|
| Offering | Course overview | Syllabus and schedule |
|
|
|:---|:---|:---|
|
|
| **Fall 2023** | [Course website](https://sites.google.com/g.harvard.edu/cs249-tinyml-2023/home) | [Syllabus](https://docs.google.com/document/d/1wu5g_e8LFYtwF8zjAKtYGBhxvMNW5IjVUefBYLkzwJw/edit) |
|
|
| **Fall 2022** | [Course website](https://sites.google.com/g.harvard.edu/tinyml/home) | [Syllabus](https://docs.google.com/document/d/1Diyv7wDlM0o2f8OKl9bv6kYecNTl9MbECXKPvhPTcF0/edit) |
|
|
| **Fall 2020** | [Course website](https://sites.google.com/g.harvard.edu/tinyml-fall2020/home) | [Syllabus and schedule](https://docs.google.com/spreadsheets/d/1LVnBw8RoT6BHd2ZETGpYyNhgV-WICVhnapw9_EILfG4/htmlembed?gid=1978935107) |
|
|
|
|
Project showcases from
|
|
[2023](https://sites.google.com/g.harvard.edu/cs249-tinyml-2023/fall-2023-final-projects)
|
|
and [2022](https://sites.google.com/g.harvard.edu/cs249-tinyml-2023/fall-2022-final-projects)
|
|
remain on the original course site. Selected projects with public code:
|
|
|
|
- [Cache 4 Trash](https://github.com/AditiR-42/cache-4-trash): waste sorting with
|
|
a Nicla Vision classifier and a motorized sorter.
|
|
- [Activity recognition and ultrasound power control](https://github.com/euranofshin/ultrasound-power-tinyml):
|
|
activity recognition on a Nicla Vision that controls ultrasound power.
|
|
- [Air Guitar](https://github.com/RobJMal/Air-Guitar-CS249R): gesture
|
|
recognition from motion and finger-flex sensors on a Teensy board.
|
|
|
|
The [course directory](../index.qmd) lists TinyML courses at other institutions.
|
|
|
|
*Links reviewed October 21, 2026.*
|