Simple C++ Neural Network Library
by darren horrocksThe C++ library (source on github) is designed to be a core neural network library, implementing basic neurons, layers and networks and comes with some basic learning methods too. The library is complete enough for those who want to learn and understand neural networks and how they are put together, but by no means is intended to be a complete AI library.
(Originally based On Neural Networks on C#)
Main Classes

Neuron  An abstract base class for all neurons. Encapsulates entities like a neuron’s weight, output value, and input value. Other neuron classes inherit from the base class.

Layer  A collection of neurons. This is a base abstract class, which encapsulates common functionality for all neuron’s layers.

Network  A collection of layers. This is an abstract base class for a layered neural network.

IActivationFunction  Pure virtual interface for activation functions. Activation functions are used in activation neurons  the type of neuron, where the weighted sum of its inputs is calculated and then the value is passed as input to the activation function, and the output value becomes the output value of the neuron.

IUnsupervisedLearning  Pure virtual interface for an unsupervised learning algorithms  the type of learning algorithms where a system is provided with sample inputs only during the learning phase, but not with the desired outputs.

ISupervisedLearning  Pure virtual interface for a supervised learning algorithms  this type of learning algorithms where a system is provided with sample inputs, with desired output values during the learning phase.
Architecture

Activation Network  The neural network where each neuron computes its output as the activation function’s output, and the argument is a weighted sum of its inputs combined with the threshold value. The network may consist of a single layer, or of multiple layers. Trained with supervised learning algorithms, the network allows to solve such tasks as approximation, prediction, classification, and recognition.

Distance Network  The neural network where each neuron computes its output as a distance between its weight values and input values. The network consists of a single layer, and may be used as a base for such networks like Kohonen Self Organizing Map, Elastic Network, and Hamming Network.
Learning
Different learning algorithms are used to train different neural networks, and are used to solve different problems:

Perceptron Learning  the algorithm may be considered as the first neural network learning algorithm, and its history starts from 1957. The algorithm may be used with a onelayer activation network, where each neuron has a threshold activation function. The range of its applications are rather small and limited the with classification of linearly separable data.

Delta Rule Learning  the algorithm is a next step after the perceptron learning algorithm. It utilizes the activation function’s derivative, and may be applicable to singlelayer activation networks only, where each neuron has a continuous activation function instead of a threshold activation function. The most popular continuous activation function is the unipolar and bipolar sigmoid function. Because the algorithm may be applied to onelayer networks only, it is limited to some classification and recognition tasks mostly.

Back Propagation Learning  this is one of the most popular and known algorithms for multilayer neural network learning. Initially, it was described in 1974, and from that time, it was extensively studied and applied to a broad range of different tasks. Because the algorithm is able to train multilayer neural networks, the range of its applications is very great, and includes such tasks as approximation, prediction, object recognition, etc.

SOM Learning  this algorithm was developed by Kohonen, and may be considered as one of the most famous unsupervised learning algorithms for clusterization problems. It treats neural network as a 2D map of nodes, where each node may represent a separate class. The algorithm organizes a network in such a way, that it becomes possible to find the correlation and similarities between data samples.

Elastic Network Learning  the algorithm is similar to the idea of the SOM learning algorithm, but it treats network neurons not as a 2D map of nodes, but as a ring. During the learning procedure, the ring gets some shape, which represents a solution. One of the most common demonstrations of this learning algorithm is the Traveling Salesman Problem (TSP).