Skip to content
ottobonilla95Public

About

9,056 hidden units. Zero training. A visual neural network with mathematically constructed weights, an interactive drawing lab, and reproducible shape-recognition tests.

Topics

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Repository files navigation

Tiny NN

9,056 hidden units. Zero training.

Tests Python License: MIT

A visual neural network with every weight constructed from geometry. Draw a shape, inspect the closest pattern, and see why the network recognizes it or returns “unknown.”

No training loop, pretrained weights, or GPU. Just Python, NumPy, Pillow, and a small drawing lab.

The Tiny NN drawing lab recognizing a cross and showing the closest geometric pattern

What can it recognize?

Crosses · square outlines · circle outlines · horizontal lines · vertical lines

Each input is a 16×16 grayscale image. The network compares it with thousands of geometric patterns, then rejects weak or ambiguous matches.

Inside the model Count
Input pixels 256
Hidden units 9,056
Fixed connection weights 1,804,895
Training steps 0

The weights follow repeated mathematical rules; they are not 1.8 million independently chosen numbers. This is geometric template matching expressed as a neural network.

Run the drawing lab

Install uv, then:

git clone https://github.com/ottobonilla95/tiny-nn.git
cd tiny-nn
uv sync
uv run tiny-nn build
uv run tiny-nn demo --open

The lab opens at http://127.0.0.1:8765. Draw a shape, try an example, erase pixels, and watch the scores change. The panel beside the grid shows the closest geometric pattern. You can also save your drawing as a PNG.

uv manages the Python 3.12 environment and installs the locked dependencies. Everything runs locally on the CPU. Stop the server with Ctrl-C; use --port 8766 if port 8765 is busy.

Test your own image

# A light shape on a dark background, including PNGs saved from the lab.
uv run tiny-nn predict drawing.png

# Dark ink on a light background.
uv run tiny-nn predict drawing.png --invert

Images are resized and padded to 16×16. Keep one simple shape in the frame. The returned match scores measure similarity, not probability.

Does it work?

The fixed model scored 93.8% on 1,500 fresh synthetic test images, after the design was developed using a separate set of 500 images.

Test Result
Overall, including unknown examples 93.8%
Known shapes 94.8%
Clean shapes 97.3%
Unknown examples correctly rejected 89.7%

The test images use an independent drawing implementation, with varying positions, sizes, stroke widths, noise, and gaps. Exact development images are excluded from the test set.

The main weakness: some filled blobs look like thick crosses at this resolution. Heavy noise also hurts. These results describe synthetic shapes; freehand drawings are a further experiment.

See the full evaluation, including mistakes · Read the recorded metrics

How can a neural network work without training?

A neural network computes with weights. For a narrow task whose rules we know, we can derive those weights directly.

Tiny NN builds patterns for each shape at different positions, sizes, and stroke widths. Fixed ReLU features handle soft pixel edges, template detectors measure the match, and max pooling picks the strongest result in each shape family. A fixed threshold decides when to answer “unknown.”

flowchart LR
    A[256 input pixels] --> B[Fixed intensity features]
    A --> C[7,007 shape detectors]
    B --> C
    C --> D[Best match per shape]
    D --> E[Shape or unknown]
Loading

No weights are fitted to examples. Development images helped improve the design; the final test was evaluated after the weights were fixed.

Explore the architecture and weight formulas

Explore the code

File What it does
network.py Constructs the weights and runs the network
dataset.py Draws independently labeled test images
evaluate.py Measures accuracy and generates reports
web.py + lab.html Connect the drawing lab to the Python model

Run the 12 automated checks:

uv run python -m unittest discover -s tests -v

Want to experiment? Add a shape family, change the geometric coverage, or investigate a failure. The contribution guide explains how to keep development and test results separate.

License

MIT © 2026 Otto Joseph.

About

9,056 hidden units. Zero training. A visual neural network with mathematically constructed weights, an interactive drawing lab, and reproducible shape-recognition tests.

Topics

Resources

Contributing

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages