AlessandroAvi/Master_Thesis

This repo contains the code developed for my master thesis

24
/ 100
Experimental

This project explores how machine learning models deployed on small, low-power microcontrollers can continuously learn and adapt to new data in real-world scenarios. It takes sensor data, like accelerometer readings for gesture recognition or camera images for digit classification, and trains a model on a microcontroller to recognize an initial set of items, then adds new items over time without forgetting the old ones. This is designed for engineers or researchers working with embedded systems and TinyML who need their devices to evolve their recognition capabilities on the fly.

No commits in the last 6 months.

Use this if you need to deploy machine learning models on microcontrollers for tasks like gesture or image recognition, where the device must learn new categories or adapt to changing data patterns over its lifetime.

Not ideal if you are working with large-scale, cloud-based machine learning applications or if your models are trained once and do not require on-device adaptation or learning of new classes.

Embedded ML TinyML Gesture Recognition Image Classification On-device Learning
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 11 / 25

How are scores calculated?

Stars

13

Forks

2

Language

C

License

Last pushed

Mar 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AlessandroAvi/Master_Thesis"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.