This project is a self-contained, complete, solution to the XOR problem written in pure Rust.
This is a classical AI problem, that is infamous becuase it represents a very simple, yet non-linear relationship. The problem is considered one cause of the so called "AI Winter" of the 1970s. Fortunately, it is solvable with only 1 Input and 1 Hidden-Layer of two neurons each in a modern feed-forward artificial neural network, using any combination of Rectified-Linear, Sigmoid & Hyperbolic Tangent functions.
Explanation of Modern feed-forward artificial neural networks: https://en.wikipedia.org/wiki/Feedforward_neural_network#Multilayer_perceptron
The number of layers, number of neurons per layer and activation functions to be used within the network are all customisable within main.rs.
cargo run --release