CARRIER 9600  ·  LOCK ACQUIRED  ·  ← BAUDHOUSE

09  ·  OPEN SOURCE

SUNSPOT

A neural network in C99. No libraries.

A dependency-free neural network written from scratch in C — including convolutional and max-pooling layers — that trains a roughly 99.3% accurate MNIST classifier and beats classical baselines at forecasting the solar cycle.

VERSION
1.7.0
RELEASED
2026-06-10
SIZE
79 KB · WIN X86-64
LICENSE
MIT
SHA256

WHAT IT DOES

NO DEPENDENCIES AT ALL

C99 and the standard math library. No BLAS, no framework, no Python. The whole engine is readable in an afternoon.

A REAL NETWORK, NOT A TOY

Dense, convolutional and max-pooling layers; sigmoid, tanh, ReLU and softmax; MSE and cross-entropy; SGD with momentum and Adam; Xavier and He initialisation; L2 decay.

THE MATH IS CHECKED

Convolutional backpropagation is verified against finite-difference gradients, and the whole thing is tested, benchmarked and built in CI on Linux, macOS and Windows.

WHAT IT DOESN'T DO

THE HONEST PART

It is CPU-only and single-machine. There is no GPU path, so it trains at the speed C and your cores allow.

It is not a framework and will not replace one. It is the thing underneath a framework, written out in full so you can read it.

The solar-cycle forecast is a statistical model beating classical baselines, not a physical simulation of the Sun.

VERIFY THE BITS

SHA-256
# PowerShell — check the archive against the published hash
Get-FileHash .\neuralnet-windows-x86_64.tar.gz -Algorithm SHA256
# expected:
76e907de9b586b76526c9a75fe4425aab5cee7fb76bc117b3326c1d427d04542

SHA256SUMS.txt covering all three platform archives ships with every release.