nesl/neurosymbolic-tinyml

TinyNS: Platform-Aware Neurosymbolic Auto Tiny Machine Learning

23
/ 100
Experimental

This project helps embedded systems engineers and researchers automatically design and deploy intelligent, interpretable AI models on small, resource-constrained microcontrollers. It takes your raw sensor data or other input and produces optimized C code for neurosymbolic models that perform tasks like activity recognition or object tracking, while guaranteeing it will run on specific hardware. The ideal user is an engineer building tinyML applications where both machine learning performance and adherence to system rules are critical.

No commits in the last 6 months.

Use this if you need to deploy complex AI that combines the reliability of symbolic logic with the power of neural networks onto microcontrollers with very limited memory and processing power, and you want the system to automatically optimize for your specific hardware.

Not ideal if you are working with large-scale cloud-based AI deployments or if you don't require platform-specific hardware optimization for your machine learning models.

embedded-systems tinyML microcontroller-programming AI-on-the-edge resource-constrained-devices
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

25

Forks

Language

C

License

BSD-3-Clause

Last pushed

Jun 02, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/nesl/neurosymbolic-tinyml"

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