njadNissi/AI_from_scratch
Building Simple versions of AI (ML, DL, NN) models from scratch to help grasp the concepts
This project helps embedded systems engineers and IoT solution architects bring AI capabilities directly to small, low-power devices like microcontrollers, smart appliances, and industrial sensors. It provides a foundation for developing and deploying machine learning models that can run locally on edge devices, allowing them to make real-time decisions without constant cloud connectivity. The project takes raw sensor data or real-world inputs and produces optimized, deployable AI models ready for resource-constrained hardware.
109 stars.
Use this if you need to integrate machine learning into Internet of Things (IoT) devices or embedded systems, enabling them to process data and make intelligent decisions on-device.
Not ideal if your primary goal is developing complex, large-scale cloud-based AI solutions with extensive computational resources.
Stars
109
Forks
4
Language
Python
License
—
Category
Last pushed
Dec 27, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/njadNissi/AI_from_scratch"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
uxlfoundation/scikit-learn-intelex
Extension for Scikit-learn is a seamless way to speed up your Scikit-learn application
INRIA/scikit-learn-mooc
Machine learning in Python with scikit-learn MOOC
ddbourgin/numpy-ml
Machine learning, in numpy
nubank/fklearn
fklearn: Functional Machine Learning
gavinkhung/machine-learning-visualized
ML algorithms implemented and derived from first-principles in Jupyter Notebooks and NumPy