↑↓ move · ↵ open · esc close

← Categories/01

AI and machine learning

Models that learn to interpret images, sound and other sensor data.

How I approach it

Machine learning is only convincing when it is measured against a classical method. I start from the geometry or physics of the problem, build a classical baseline, then train a model and compare the two on the same data.

Tools
PythonPyTorchTensorFlowscikit-learnONNXOpenCV

6 projects

Series

Computer vision: Where is this thing?

Three projects on one question, with different sensors.

Read the series→
Featured
AI and machine learning

Stereo vision lab

Place two virtual cameras in a 3D scene, change baseline and focal […]

Three.jsONNX+1
All work in this area
AI and machine learning

HARNAIS SSI

A cybersecurity harness for AI coding agents such as Claude Code […]

CybersecurityAI agents
AI and machine learning

3D reconstruction from images

From a handful of photos to a point cloud and a navigable 3D scene […]

COLMAPGaussian splatting+1
AI and machine learning

Sound source localization

Find where a sound comes from using the delay between microphones […]

Web AudioTDOA+1
Related areas

Algorithms and games

Search, planning, play →

Software and apps

Desktop, web, systems →

Community and open source

Pull requests, plugins, tools →

Creative coding and motion

Animation, 3D, generative visuals →

Design and branding

Logos, interfaces, systems →