Data
Collect & shape the signal.
Every model starts as a cloud of examples. Cleaning, labelling and augmenting that cloud is half the craft. Garbage in, garbage out.
Neural engineering × immersive 3D
I design neural networks from first principles and turn them into real-time, interactive experiences: the math, the model and the motion, under one roof.
02 — Manifesto
Most products rent their intelligence. I write mine, from the first matrix multiply to the last pixel on screen. The networks further down this page have no TensorFlow and no PyTorch behind them: just hand-written math, learning live in your browser.
03 — How a model is born
Collect & shape the signal.
Every model starts as a cloud of examples. Cleaning, labelling and augmenting that cloud is half the craft. Garbage in, garbage out.
Design the network.
Layers, widths, activations, initialisation. Choosing the shape of the function before it learns anything decides what it can learn.
Descend the loss landscape.
Backpropagation works out how every weight should change, and an optimiser like Adam takes the step. The glowing trail is one descent into a valley.
Ship it where people are.
In the browser, at the edge, on device. Fast, private inference inside an interface people actually enjoy using.
04 — The Models
No ML libraries. Each model has its forward pass, backpropagation and optimiser hand-written in JavaScript, and trains in your browser right now: one learns to classify, one learns to write, one learns to balance.
backward() running on this page
backward(), derived by hand
update(): learning from its own trial and error
05 — What I build
Custom architectures designed, implemented and trained from first principles, or with PyTorch and JAX when the job calls for scale.
Hand-written GLSL, GPU particle systems and post-processing pipelines. The background of this page is one.
Scroll-driven stories, physics-based motion and small interactions that make complex ideas feel easy.
Models that run where your users are: in the browser, at the edge, on device. Private, fast and cheap to serve.