BrabeNetz 1.4.3

There is a newer version of this package available.
See the version list below for details. 
dotnet add package BrabeNetz --version 1.4.3                

                    
                

            
NuGet\Install-Package BrabeNetz -Version 1.4.3
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="BrabeNetz" Version="1.4.3" />
For projects that support PackageReference, copy this XML node into the project file to reference the package. 
paket add BrabeNetz --version 1.4.3                

                    
                

            
#r "nuget: BrabeNetz, 1.4.3"
#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 BrabeNetz as a Cake Addin
#addin nuget:?package=BrabeNetz&version=1.4.3

// Install BrabeNetz as a Cake Tool
#tool nuget:?package=BrabeNetz&version=1.4.3

BrabeNetz

🌐 A fast and clean supervised neural network in C++, capable of effectively using multiple cores 🧠

Usage

  1. Build & link library

  2. Constructors

    1. network(initializer_list<int>, properties): Create a new neural network with the given topology vector and properties and fill it with random numbers ({ 2, 3, 4, 1} = 2 Input, 3 Hidden, 4 Hidden, 1 Output Neurons - total of 4 layers)
    2. network(network_topology&, properties): Create a new neural network with the given network topology and load_ it's values
    3. network(string, properties): Create a new neural network with the given path to the sate.nn file and load it

  3. Functions

    1. double* feed(double[] input_values): Feed the network input_values and return an array of output values (where the array's length is the size of the output layer in topology)
    2. double* train(double[] input_values, double[] expected_output, double& out_total_error): Feed the network input_values and backwards-propagate to adjust the weights/biases and reduce error. Returns the output layer's values, out_total_error will be set to the total error of the output layer (This can be used to check if more training is needed)
    3. void save(string path): Save the current network state (topology, weights, biases) to disk (with the given path or default: state.nn)
    4. void set_learnrate(double value): Set the learn rate of the network (used by train(..) function). Should either be a constant (0.5) or 1 / (total train times + 1)
    5. network_topology& build_topology(): Build and set the network topology object of the current network's state (Can be used for network visualization or similar)

Usage examples can be found here, and here

Product Compatible and additional computed target framework versions.
native native is compatible. 
Compatible target framework(s)
Included target framework(s) (in package)
Learn more about Target Frameworks and .NET Standard.

This package has 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
1.5.2 1,474 2/1/2018
1.5.0 1,119 1/25/2018
1.4.5 1,073 1/18/2018
1.4.3 1,237 1/18/2018
1.4.2 1,158 1/18/2018
1.4.1 1,166 1/18/2018
1.4.0 1,039 1/18/2018

Performance improvements, Code cleanup, Properties parameters