Skip to content

Simple Customisable neural network solution to the XOR problem, in rust.

License

Notifications You must be signed in to change notification settings

KierPalin/Rust-Neural-Network-XOR-Problem

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

9 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Overview

This project is a self-contained, complete, solution to the XOR problem written in pure Rust.

XOR Problem

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

Customisability

The number of layers, number of neurons per layer and activation functions to be used within the network are all customisable within main.rs.

Execution

cargo run --release

About

Simple Customisable neural network solution to the XOR problem, in rust.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages