LittleNN 1.0.2

.NET 5.0 This package targets .NET 5.0. The package is compatible with this framework or higher.
Additional Details

Some neural network functions have private access.
The neuron activation function is only sigmoid.

There is a newer version of this package available.
See the version list below for details. 
dotnet add package LittleNN --version 1.0.2                

                    
                

            
NuGet\Install-Package LittleNN -Version 1.0.2
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="LittleNN" Version="1.0.2" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add LittleNN --version 1.0.2                

                    
                

            
#r "nuget: LittleNN, 1.0.2"
#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 LittleNN as a Cake Addin
#addin nuget:?package=LittleNN&version=1.0.2

// Install LittleNN as a Cake Tool
#tool nuget:?package=LittleNN&version=1.0.2

LittleNN

Introduction

  • The expectation is to provided a neural network minimization implementation.
  • TargetFramework is net5.0. You can modify it according to your needs.
  • All of the code is written in C#, and the project use the MIT LICENSE.
  • Get more info from repository README.
  • If you need faster performance, it is recommended to use other popular deep learning frameworks such as TensorFlow, PyTorch, or Keras.

Usage

Example1 Xor Operator

Input A Input B Output
1 1 0
1 0 1
0 1 1
0 0 0

Code

NeuralNetwork network = new NeuralNetwork(2, new int[] { 6, 6, }, 1);

StandardData[] dataSets = new StandardData[]
{
  new StandardData(new float[] { 1f, 1f }, new float[] { 0f }),
  new StandardData(new float[] { 0f, 1f }, new float[] { 1f }),
  new StandardData(new float[] { 1f, 0f }, new float[] { 1f }),
  new StandardData(new float[] { 0f, 0f }, new float[] { 0f }),
};

Random random = new Random();
for (int i = 0; i < 1000 * 1000; i++)
{
    StandardData dataSet = dataSets[random.Next() % dataSets.Length];
    float error = network.Train(dataSet);
    if (i % (20 * 1000) == 0)
        // Expect: The error will decrease gradually
        Console.WriteLine($"{i}   : {error}");
}

Example2 OCR Number Recognize

  • Get more info from repository README.

Example3 Serialize

  • Get more info from repository README.
Product Compatible and additional computed target framework versions.
.NET net5.0 is compatible.  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. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

NuGet packages

This package is not used by any NuGet packages.

GitHub repositories

This package is not used by any popular GitHub repositories.