Machine learning / 2026 / Runs natively
Meme Detector
An image classification pipeline trained to recognise meme formats from a curated dataset.
01
The problem
Format recognition needs data that doesn't exist in a clean dataset.
02
How I approached it
Built the dataset and training pipeline together so labelling decisions and model behaviour could be revised in step.
03
The outcome
A working classifier over a self-built corpus.
Related work
A neural network that learns chess by distilling Stockfish, with MCTS on top and a proper Elo measurement against Stockfish itself.
A reverse GitHub for AI-written work. Give it a repository, gist, pull request, package or web page and it returns a calibrated estimate of whether the work was AI-generated, with the file, commit or line that shows why.
A 26 KB neural network running entirely in a browser tab. Draw a digit, it classifies on device, and the page reports which execution provider it actually got and what the inference cost.