https://github.com/littensy/nanoai

✨ Minimal library for creating neural networks
https://github.com/littensy/nanoai

machine-learning neural-network roblox roblox-ts typescript

Last synced: 30 days ago
JSON representation

✨ Minimal library for creating neural networks

• Host: GitHub
• URL: https://github.com/littensy/nanoai
• Owner: littensy
• License: mit
• Created: 2024-05-27T04:23:57.000Z (8 months ago)
• Default Branch: main
• Last Pushed: 2024-09-02T16:32:29.000Z (4 months ago)
• Last Synced: 2024-11-22T10:30:32.185Z (about 2 months ago)
• Topics: machine-learning, neural-network, roblox, roblox-ts, typescript
• Language: Luau
• Homepage:
• Size: 50.8 KB
• Stars: 8
• Watchers: 1
• Forks: 1
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE.md

Awesome Lists containing this project

README

        


  


	

  

  
Nanoai

  


    Minimal library for creating neural networks.

    


    npm package →

  




![GitHub Workflow Status](https://img.shields.io/github/actions/workflow/status/littensy/nanoai/ci.yml?style=for-the-badge&branch=master&logo=github)

[![NPM Version](https://img.shields.io/npm/v/@rbxts/nanoai.svg?style=for-the-badge&logo=npm)](https://www.npmjs.com/package/@rbxts/nanoai)

[![GitHub License](https://img.shields.io/github/license/littensy/nanoai?style=for-the-badge)](LICENSE.md)



**Nanoai** is a fast, lightweight library for handling multi-layer perceptron (MLP) neural networks.

The addition of recurrent and convolutional layers is not planned at this time.

## 📦 Setup

### TypeScript

```sh

npm install @rbxts/nanoai

yarn add @rbxts/nanoai

pnpm add @rbxts/nanoai

```

### Wally

Add `littensy/nanoai` to your `wally.toml` file.

```toml

[dependencies]

Nanoai = "littensy/nanoai@VERSION"

```

## 📚 API Reference

#### `create(shape, activation)`

#### `predict(network, input)`

#### `backpropagate(network, input, expected, learningRate)`

#### `evolution(options)`

#### `init[type](network, ...)`

#### `initialize(network, initializer)`

#### `clone(network)`

## 🚀 Examples

### XOR problem

```lua

local model = Nanoai.create({ 2, 3, 1 }, Nanoai.Activation.TanH)

Nanoai.init.normal(model)

for _ = 1, 500 do

	Nanoai.backpropagate(model, { 0, 1 }, { 1 }, 0.3)

	Nanoai.backpropagate(model, { 1, 0 }, { 1 }, 0.3)

	Nanoai.backpropagate(model, { 0, 0 }, { 0 }, 0.3)

	Nanoai.backpropagate(model, { 1, 1 }, { 0 }, 0.3)

end

Nanoai.predict(model, { 0, 1 }) -- ~1

```

---



Nanoai is released under the MIT License.





[![MIT License](https://img.shields.io/github/license/littensy/nanoai?style=for-the-badge)](LICENSE.md)