← All projects
AI / MLIn progress

Edge AI Lab — ML on the device

My next flagship: taking models from a Jupyter notebook down to resource-constrained hardware — quantisation, latency budgets and real sensor data. Combines both halves of my career.

In progress
PythonPyTorchTinyMLQuantizationRaspberry Pi
  1. 1Pick a sensor problem & collect data← now
  2. 2Train a baseline model in Python
  3. 3Quantise & prune for the edge
  4. 4Deploy & benchmark on device
  5. 5Write it up on the blog

▶ Try it · neural net playground

tap / drag to add points

epoch

0

loss

–

accuracy

–

points

0

A real neural network training live in your browser — no libraries, just math. Add points and watch it learn.


Why this project

Most ML portfolios stop at a notebook. Most embedded portfolios never touch a model. This project is where both meet: train a model, compress it, and make it run on real hardware within real latency and memory budgets.

Plan

  1. Pick a sensor-driven problem (e.g. audio keyword spotting or vibration anomaly detection).
  2. Train a baseline in Python and document the metrics.
  3. Quantise / prune it and measure accuracy vs. size vs. latency.
  4. Deploy on-device and write up everything on the blog.

This page will be updated as the project progresses.