aigo

AIGO

Simple and extensible AI models in Go for learning and experimentation

I - Introduction

AIGO is a library designed to provide comprehensive access to AI models.
The primary role of AIGO is to be a self-teaching, fun project and a good introduction to Machine Learning,
but it can also be used by anyone interested in AI to experiment and understand various models.

II - Install

To install AIGO in your project, you can use the following command:

go get github.com/eleby/aigo

III - Use

A usage example of each model is available in the examples folder.

Perceptron

The Perceptron is a simple linear classifier that can be used for binary classification tasks.
It learns a linear decision boundary by adjusting weights based on the input data and the expected output.
Here is a basic example of how to use the Perceptron model in your Go code:

package main

import (
    "fmt"
    "github.com/eleby/aigo/perceptron"
)

func main() {
    // Training data: logical AND
    inputs := [][]float64{
        {0, 0}, {0, 1}, {1, 0}, {1, 1},
    }
    expected := []float64{0, 0, 0, 1}

    // Create and train perceptron
    neuron, err := perceptron.NewPerceptron(inputs, expected, 0.1)
	if err != nil {
        panic("Error creating perceptron:" + err.Error())
    }
	neuron.Train(10000)

    // Test predictions
    fmt.Println("Predict [1,1]:", neuron.PredictClass([]float64{1, 1})) // 1
    fmt.Println("Predict [0,1]:", neuron.PredictClass([]float64{0, 1})) // 0
}

IV - Structure

.
├── perceptron/             # Implementation of the Perceptron model
├── examples/               # Usage examples of each model
│   └── perceptron/         # Usage examples of the Perceptron model
│       ├── main.go         # Main entry point to run the Perceptron example
│       ├── data/           # Data used for the Perceptron model
│       └── preprocessing/  # Preprocessing utilities for the Perceptron data
└── README.md               # <- You are here

V - Tests

To run the tests for the Perceptron model, you can use the following command in the Aigo directory :

go test ./perceptron

VI - Data

You can find various examples of data formats to use with the models.
Typically, the Perceptron model uses a slice of slices of floats.
You can see examples of this format in the perceptron/perceptron_test.go file (raw coded input data)
or in the examples/perceptron/data folder (CSV files).

VII - Roadmap

This project aims to evolve with time. Here is AIGO's roadmap :

• Add Perceptron model
• Add MLP (Multi-Layer Perceptron) model
• Add CNN (Convolutional Neural Network) model ?
• Add RNN (Recurrent Neural Network) model ?

VIII - Contributing

Contributions are welcome!
If you'd like to improve AIGO, here are the steps:

1. Fork the repository
2. Create your feature branch (git checkout -b feature/my-feature)
3. Commit your changes (git commit -m 'Add my feature')
4. Push to the branch (git push origin feature/my-feature)
5. Open a Pull Request

Feel free to open issues as well if you encounter bugs or have feature suggestions.

IX - License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.

X - Changelog

See the CHANGELOG file for the list of changes made to the project.