Educational Implementation · Rust
trot-livive-net
A tiny neural network written in Rust, compiled to WASM, trained in your browser, exported to ONNX. Every number visible: weights, gradients, loss, forward pass. Built to be read, not just run.
What it is
TROT is an educational implementation of a tiny neural network written from scratch in Rust, featuring hand-written forward and backward passes, deterministic data generation, and ONNX export with runtime verification, designed to teach the fundamentals of machine learning through transparency.
Where it counts
- Machine Learning90%
- Data Science20%
- MLOps20%
- NLP & LLMs10%
How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.
Around it on the Machine Learning board
Whole board- 3, shared rankmodded-GLM-5.3-flash-from-scratchEducational Implementation · Python66.0AdvancedPop AlexandruMachine Learning
- 3, shared rankORBIT-allTraining Experiment · Python66.0AdvancedPop AlexandruMachine Learning
- 05trot-livive-netEducational Implementation · Rust65.5AdvancedJarad PeckenpaughMachine Learning
- 06, shared rankcamera505ML Application · Python64.6Advancedvlad andreiMachine Learning
- 06, shared rankmines-smLibrary / Framework · Rust64.6AdvancedJarad PeckenpaughMachine Learning
