It is known fact, that there are many different problems, for which it is difficult to find formal algorithms to solve them. Some problems cannot be solved easily with traditional methods; some problems even do not have a solution yet. For many such problems, neural networks can be applied, which demonstrate rather good results in a great range of them. The history of neural networks starts in 1950-ies, when the simplest neural network's architecture was presented. After the initial work in the area, the idea of neural networks became rather popular. But then the area had a crash, when it was discovered that neural networks of those times are very limited in terms of the amount of tasks they can be applied to. In 1970-ies, the area got another boom, when the idea of multi-layer neural networks with the back propagation learning algorithm was presented. From that time, many different researchers have studied the area of neural networks, what lead to a vast range of different neural architectures, which were applied to a great range of different problems. For now, neural networks can be applied to such tasks, like classification, recognition, approximation, prediction, clusterization, memory simulation, and many other different tasks, and their amount is growing.
In this article, a C# library for neural network computations is described. The library implements several popular neural network architectures and their training algorithms, like Back Propagation, Kohonen Self-Organizing Map, Elastic Network, Delta Rule Learning, and Perceptron Learning. The usage of the library is demonstrated on several samples:
Classification (one-layer neural network trained with perceptron learning algorithms);
Approximation (multi-layer neural network trained with back propagation learning algorithm);
Time Series Prediction (multi-layer neural network trained with back propagation learning algorithm);
Color Clusterization (Kohonen Self-Organizing Map);
Traveling Salesman Problem (Elastic Network).
The attached archives contain source codes for the entire library, all the above listed samples, and some additional samples which are not listed and discussed in the article.
The article is not intended to provide the entire theory of neural networks, which can be found easily on the great range of different resources all over the Internet, and on CodeProject as well. Instead of this, the article assumes that the reader has general knowledge of neural networks, and that is why the aim of the article is to discuss a C# library for neural network computations and its application to different problems.