--- Release 1.0 --- 2009-09-02 BlackLight <blacklight@autistici.org> * all: Most of the code has been rewritten. Now a trained network should be saved, via save() method, to an XML file, and loaded from that using the constructor. This way is much cleaner, and easily fixable and customizable too. The old approach through binary files has been kept yet through saveToBinary() and loadFromBinary() methods, for back-compatibility purposes, though it's strongly deprecated. Moreover, the XML formats (for training the network and for loading a trained network's information) are fully compatible with the ones used by NeuralPerl module, mostly a Perl version of this library, so you can use the same XML files to train and load a neural network using C++ and Perl. Moreover, a great step forward in the fixing of the dirty old vulnerability (synaptical random weights overflow) has been made, keeping the values of the weights very low and ~ 0. I've made tons of tests and the network never overflowed. Anyway, if you should experience an overflow (synaptical weights go > 1), just write me. I've also done a deep re-design of library's classes, using as public methods only the stuff you *REALLY* need to be public. --- Release 0.4 --- 2009-08-16 BlackLight <blacklight@autistici.org> * all: Now it *REALLY* supports multiple output values, i.e. multiple neurons, in the output layer. Oh, and I've fixed too that nasty bug that made training from sets containing more than a single training set. Added examples in the Doxygen documentation. * neuron.cpp: Fixing propagate() function 2009-08-15 BlackLight <blacklight@autistici.org> * Makefile: Now you compile Neural++ with -Wall -pedantic -pedantic-errors -ansi. And you won't get a single error. I love writing pedantic, pure ISO C++ code... * all: Hey I can't believe it guys, I've fixed that horrible bug an neural output won't diverge anymore ^^ Also removed the 'deriv' parameter, as function pointer. It was just useless, as once you have an activation function, you can compute its derivate in any points. But, of course, this makes old codes no more compatible with this new version. --- Release 0.3 --- 2009-08-09 BlackLight <blacklight@autistici.org> * Makefile: Totally changed * neural++.hpp: Changed header name, added BETA0 macro * synapsis.cpp: Added momentum() method to compute the inertial momentum of a synapsis * all: Data type changed from float to double for everything, fixing neuralpp namespace, fixed indentation, fixed exception throwing, fixed documentation --- Release 0.2.2 --- 2008-11-04 BlackLight <blacklight@autistici.org> * all: Added initXML(), XMLFromSet() and closeXML() methods to auto- generate training XML. train() method can now get XML both from a file and from a simple string. --- Release 0.2.1 --- 2008-10-22 BlackLight <blacklight@autistici.org> * all: Added `train()` method to NeuralNet class, that allows you to train a neural network using an XML containing pre-saved training sets (input values, expected output). See examples/adder.xml for an example of such XML. --- Release 0.2 --- 2008-10-12 BlackLight <blacklight@autistici.org> * all: Added `save()` method to NeuralNet class, that allows you to save a trained neural network to a binary file, to load anytime you need using NeuralNet(const char *fname) constructor. --- Release 0.01b --- 2008-04-03 BlackLight <blacklight@autistici.org> * all: First beta release ^^ Copyright 2008, 2009, BlackLight Copying and distribution of this file, with or without modification, are permitted provided the copyright notice and this notice are preserved.