C++ implementation of neural networks trainer

The paper is going to introduce a revised C++ version of neural network trainer (NNT) which is developed based on neuron by neuron computation. Besides traditional error back propagation (EBP) algorithm, two improved version of Levenberg Marquardt (LM) algorithm and a newly developing algorithm are also implemented. The software can handle not only conventional multilayer perceptron networks, but also arbitrarily connected neuron networks. Comparing with the original NNT developed based on MATLAB [18], the revised version can handle much larger networks and the training speed is also improved as 50 to 100 times faster. Several practical applications are presented to show the power of this training tool. The software is available for everyone on the website.