The Perceptron Apparatus is a 1.2-metre-diameter wooden instrument with six concentric rings: five of brass sliders, which hold the numbers in a simple neural network, and a circular slide rule. You move the sliders by hand to perform matrix multiplication and ReLU activation — turning what’s usually an invisible cascade of floating-point arithmetic into something you can see and touch.

The Perceptron Apparatus: a large circular wooden instrument with concentric rings of sliders.
The Perceptron Apparatus — laser-cut and CNC-routed plywood, 1.2 m in diameter. Photo credit: Andrew Meares.

Where does the intelligence live?#

Digital computers hide computation behind layers of abstraction. The apparatus does the opposite. It makes you do the work — moving sliders, reading off values, carrying numbers forward through the network. You become the “human computer” in the neural network calculation. And rarely on your own: the apparatus is large enough that a single classification becomes a few-handed affair, one person reading off weights while another works the sliders.

This matters because it forces a strange question. If a neural network is intelligent, where does that intelligence reside? In the weights? In the architecture? In the person moving the sliders? The apparatus sits somewhere between a séance and a slide rule — and that ambiguity is the point. AI is built on an ontology that separates mind from material reality. Making the computation physical and embodied exposes how odd that assumption really is.

How it works#

Five of the six concentric rings map directly onto a feedforward network: input, weights, hidden layer, more weights, and output. The sixth is a logarithmic scale — essentially a circular slide rule — that handles the multiplications.

The full Perceptron Apparatus design drawn as black linework on white: five concentric rings of sliders and a logarithmic slide-rule ring around a central square, with radial spokes.
The full design: five concentric rings of sliders and a circular slide rule, laid out across the 1.2 m disc.

For MNIST digit recognition, you draw a digit on a worksheet, look up the corresponding weights on a reference poster, work the sliders, and read off the answer. Move the weight sliders to new positions and the same apparatus does a different job: classifying an animal from yes-or-no facts about it (hair, feathers, milk), or guessing the next letter of a word from the last three. Three very different domains, one shared physical form.

Detail of the Perceptron Apparatus's concentric rings and sliders.
Three jobs, one form: the same apparatus reads handwritten digits, classifies animals and guesses the next letter. Photo credit: Andrew Meares.

Every design and fabrication file is openly available in the project repository, so the whole apparatus can be remade from scratch. The trained weights are printed onto A3 reference posters and worksheets you read from as you operate it. Fabrication support came from Sam Shellard at UC Workshop7.

Is it an abacus? Is it an ouija board? No — it’s a perceptron apparatus.

In the lineage of calculating machines#

Not an abacus, then, but a cousin of one. People have built machines to compute for thousands of years: the Antikythera mechanism that tracked the heavens with bronze gears, the abacus, the slide rule, Babbage’s Difference Engine. In each of them the calculation sits right there in the movement of the parts. The Perceptron Apparatus brings a neural network, the engine behind modern AI, into that same visible, mechanical company.

What it gives up is speed. Worked by hand, the apparatus manages something like a tenth of a calculation per second: one multiply-and-add every ten seconds or so. NVIDIA’s current data-centre AI chip, the Blackwell B200, is rated at around twenty petaFLOPS, which is twenty quadrillion such operations every second. What that chip finishes in one second would take the apparatus, worked without pause, something like six billion years, longer than the Earth has existed. The apparatus spends all that speed on the one thing the chip cannot give you: a computation slow enough, and large enough, to watch.

A Cybernetic Studio project by Ben Swift (2024). Code and fabrication files: github.com/ANUcybernetics/perceptron-apparatus.

How to cite this work

Ben Swift (2025). Perceptron Apparatus. doi.org/10.5281/zenodo.20768557 ·CC BY 4.0

@misc{swift2024perceptron,
  author    = {Ben Swift},
  title     = {Perceptron Apparatus},
  year      = {2025},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.20768557},
  url       = {https://doi.org/10.5281/zenodo.20768557},
  note      = {Cybernetic Studio, ANU School of Cybernetics}
}
Research metadata
Category
Original Creative Works: Visual Art Work (Standard)
FoR codes
  • 460804 Computing education — 75%
  • 330310 Interaction and experience design — 25%

Field of Research (FoR) codes and ERA category are proposed classifications for this non-traditional research output (NTRO), pending sign-off.

You are on Aboriginal land.

The Australian National University acknowledges, celebrates, and pays our respects to the Ngunnawal and Ngambri people of the Canberra region and to all First Nations Australians on whose traditional lands we meet and work as the oldest continuing culture and knowledges in human history.

arrow-right bars search times