NeuronDotNet 3.0 is free and open source. It is released under GNU General Public License version 3.0. You can redistribute it and/or modify it under the terms of the GNU General Public License as published by the Free Software Foundation, either version 3 of the License, or (at your option) any later version.

NeuronDotNet is also available at Sourceforge.

Download Links

• NeuronDotNet 3.0 source
• NeuronDotNet 3.0 assembly
• NeuronDotNet 3.0 documentation
• NeuronDotNet Sample Applications

The sample applications demonstrate the functioning of neural networks and their applications in function modelling, classification, optimization, clustering and pattern recognition problems.

You are most welcome to send your suggestions, sample applications, code snippets, feature requests, links to your neurondotnet applications or any other kind of feedback to "neurondotnet [DOT] feedback [AT] gmail [DOT] com".

NeuronDotNet 3.0 Feature List

• Support for neural networks with any acyclic structure of layers
• One-One and Complete connectors are supported
• Backpropagation networks and Kohonen SOMs are supported
• Learning Rate changes from its initial value to a final value using a pluggable function (Linear, Logarithmic and Hyperbolic functions are built in)
• Neural network initialization modules are pluggable (Random, Constant, NguyenWidrow and Normalized Random Functions are built in)
• Custom activation funtions used in backpropagation networks are pluggable (Sigmoid, sine, tanh, logarithmic and linear functions are built in)
• For a Kohonen Layer, Neighborhood functions are pluggable (Gaussian function and mexican hat functions are built in)
• Various events are exposed which allow users to analyse how a network learns
• Kohonen layers are planar in shape. However, we can have circular rows and/or columns which make them attain the shape of a cylindrical surface or a toroidal surface.
• Hexagonal and Rectangular Kohonen lattice topologies are supported
• Training set has been defined to support Batch Training
• API to add custom network architectures and learning algorithms
• Layers, connectors, networks and training sets implement ISerializable interface

NeuronDotNet User Manual provides a brief introduction to important aspects of neural networks and a detailed information about how to design and construct neural networks, how to customize them and use them in various applications. It also explains how to use NeuronDotNet API to extend exisitng features, add custom architectures and incorporate new training algorithms.

Features currently under development

• Support for more neural network architectures
• Fuzzy logic and genetic algorithms integration
• Visual User Interface to design neural networks