introduction.txt

可以用C++语言开发各种神经网络：BP

/*! \mainpage annie - Neural Network Library
*
* Last Modified On:
*	January 13, 2003
*
* \section intro Introduction
*
* annie is an ANN, ie, Artificial Neural Network library developed in C++. It can be used
* to implement various kinds of neural networks like Multi-Layer Perceptron, Radial basis
* function networks, Hopfield networks etc.
*
* To avoid possible conflict with any other library
* that you may be using, all classes here are packaged into a namespace \em annie.
*
* This library is intended to be ideal for beginners who need to use neural networks in some particular
* application, and want to concentrate on the application rather than the network implementation itself,
* so such users can treat this library as a black-box, not worrying about how it's working.
*
* You can also download the Matlab Extensions Pack from the website (<a href="http://annie.sourceforge.net/">annie.sourceforge.net</a>), which will help you use the features of Matlab to train and modify
* networks and yet be able to use them in your C++ programs.
*
* Developed by : <a href=http://annie.sourceforge.net/contact.html>Asim Shankar</A>
*
* \section usage Getting Started
*
* \subsection startup Starting up
* All functionality is packaged in the namespace \em 'annie'. So, if you're writing a program, just do the 
* following:
*
* \code 
* #include <annie.h>
* using namespace annie;
* \endcode
*
* You can ignore the second step if you explicitly use \em annie:: before any member of the library. For example,
* \code annie::TwoLayerNetwork net(2,3,1); \endcode
* to create a 2 layer feed-forward neural network with 2 inputs, 3 hidden nodes and 1 output.
*
* Ofcourse, you have to make sure that your compiler knows where to find annie.h and should be able to link to
* the library file. See the README.txt file in the annie distribution for details.
* etc...
*/