Tinn 2.1.0

.NET Standard 2.0 This package targets .NET Standard 2.0. The package is compatible with this framework or higher. 
dotnet add package Tinn --version 2.1.0                

                    
                

            
NuGet\Install-Package Tinn -Version 2.1.0
This command is intended to be used within the Package Manager Console in Visual Studio, as it uses the NuGet module's version of Install-Package. 
<PackageReference Include="Tinn" Version="2.1.0" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add Tinn --version 2.1.0                

                    
                

            
#r "nuget: Tinn, 2.1.0"
#r directive can be used in F# Interactive and Polyglot Notebooks. Copy this into the interactive tool or source code of the script to reference the package. 
// Install Tinn as a Cake Addin
#addin nuget:?package=Tinn&version=2.1.0

// Install Tinn as a Cake Tool
#tool nuget:?package=Tinn&version=2.1.0

NuGet Version NuGet Downloads Build

Tinn: Tiny Neural Network

Tinn is a tiny and dependency free neural network implementation for dotnet. It has three configurable layers: an input layer, a hidden layer and an output layer.

How to get started?

Create a neural network:

var network = new TinyNeuralNetwork(inputCount: 2, hiddenCount: 4, outputCount: 1);

Load a data set:

// This is XOR operation example.
var input = new float[][]
{
    new []{ 1f, 1f }, // --> 0f
    new []{ 1f, 0f }, // --> 1f
    new []{ 0f, 1f }, // --> 1f
    new []{ 0f, 0f }, // --> 0f
};
var expected = new float[][]
{
    new []{ 0f }, // <-- 1f ^ 1f
    new []{ 1f }, // <-- 1f ^ 0f
    new []{ 1f }, // <-- 0f ^ 1f
    new []{ 0f }, // <-- 0f ^ 0f
};

Train the network until a desired accuracy is achieved:

for (int i = 0; i < input.Length; i++)
{
    network.Train(input[i], expected[i], 1f);
}
// Note: you will probably have to loop this for a few times until network improves.

Try to predict some values:

var prediction = network.Predict(new [] { 1f, 1f });  
// Will return probability close to 0f, since 1 ^ 1 = 0.

For more examples see the examples directory and automated tests.

The original library was written by glouw in C.

Product Compatible and additional computed target framework versions.
.NET net5.0 was computed.  net5.0-windows was computed.  net6.0 was computed.  net6.0-android was computed.  net6.0-ios was computed.  net6.0-maccatalyst was computed.  net6.0-macos was computed.  net6.0-tvos was computed.  net6.0-windows was computed.  net7.0 was computed.  net7.0-android was computed.  net7.0-ios was computed.  net7.0-maccatalyst was computed.  net7.0-macos was computed.  net7.0-tvos was computed.  net7.0-windows was computed.  net8.0 was computed.  net8.0-android was computed.  net8.0-browser was computed.  net8.0-ios was computed.  net8.0-maccatalyst was computed.  net8.0-macos was computed.  net8.0-tvos was computed.  net8.0-windows was computed. 
.NET Core netcoreapp2.0 was computed.  netcoreapp2.1 was computed.  netcoreapp2.2 was computed.  netcoreapp3.0 was computed.  netcoreapp3.1 was computed. 
.NET Standard netstandard2.0 is compatible.  netstandard2.1 was computed. 
.NET Framework net461 was computed.  net462 was computed.  net463 was computed.  net47 was computed.  net471 was computed.  net472 was computed.  net48 was computed.  net481 was computed. 
MonoAndroid monoandroid was computed. 
MonoMac monomac was computed. 
MonoTouch monotouch was computed. 
Tizen tizen40 was computed.  tizen60 was computed. 
Xamarin.iOS xamarinios was computed. 
Xamarin.Mac xamarinmac was computed. 
Xamarin.TVOS xamarintvos was computed. 
Xamarin.WatchOS xamarinwatchos was computed. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

  • .NETStandard 2.0

    • No dependencies.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.

Version Downloads Last updated
2.1.0 176 10/8/2023
2.0.0 167 7/28/2023
1.0.0 366 1/17/2021

# Changelog

All notable changes to this project will be documented in this file.

The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).

## [Unreleased]


## [2.1.0] - 2023-10-08

### Added

- `TinyNeuralNetwork` now has a constructor to provide pre-trained weights and biases.
- `TinyNeuralNetwork` weights and biases can now be accessed via read-only properties `Weights` and `Biases`.

## [2.0.0] - 2023-07-28

### Changed

- `TinyNeuralNetwork.Train` no longer calculates or returns error. To get current error values call `TinyNeuralNetwork.GetTotalError` instead.
- Improved `TinyNeuralNetwork.Load` and `TinyNeuralNetwork.Save` performance.

### Fixed

- Swapped parameters in `LossFunctionPartialDerivative`, this was a bug.
- Saving and loading is now independent of the current culture.
- Reserved 10% of training data for verification in the hand written number recognition example.

## [1.0.0] - 2021-01-18

### Added

- Initial `TinyNeuralNetwork` implementation based on [C implementation].
- Example of a hand written number recognition (MNIST database).

[unreleased]: https://github.com/lawrence-laz/tinn-dotnet/compare/v2.1.0...HEAD
[2.1.0]: https://github.com/lawrence-laz/tinn-dotnet/compare/v2.0.0...v2.1.0
[2.0.0]: https://github.com/lawrence-laz/tinn-dotnet/compare/v1.0.0...v2.0.0
[1.0.0]: https://github.com/lawrence-laz/tinn-dotnet/compare/v0.3.0...v1.0.0
[C implementation]: https://github.com/glouw/tinn