The project has mostly gone quite well. I set out to learn how to do neural network programming myself and as a part of my learning process, to explain it in a manner that would be of use to other people which I feel I haven't done too badly at, and I decided at the start that the program should be usable as a learning tool which meant that the results had to be repeatable, with the option of the person using the software to be able to change the most important parameters for each network to see what it would do. This I think has been done.
Of course, as with everything, there were setbacks along the way and I still haven't managed to get the bidirectional associative memory code to behave in the way that I would like it to.
It became apparent early on in the release cycle that the fact that I was releasing the project compiled with the 2003 version of Developer Studio was proving to be something of a draw back, and for this reason, this additional article has been added. I've reinstalled Developer Studio .NET and put together a version that runs, and to be honest, that's about the best thing I can say for it. So, if you're using the 2002 version, consider yourself disadvantaged.
As I've stated earlier, there should be no problem with the library on either version of the compiler and that assumption was right. The problems have occurred with the LogViewer and with the icons. The icons problem has been easily fixed but the LogViewer has been removed from the application all together. I was getting problems with the Internet Explorer control on the older compiler, and as I've rewritten the LogViewer at least three times since I started work on this project, I just couldn't face rewriting again at this moment in time. Besides, I've already started the next different but related project.
Links for the Developer Studio .NET version will be clearly added to the other articles in the series, so if you download and play around with it, good luck with it.
Finally, just because this is called a first release, it doesn't necessarily follow that there will be a second release. Although that bidirectional associative memory code is giving me an itch, I can't quite scratch.
- 2003 :- Initial release.
- 10 December 2003 :- Review and edit for CP conformance.
- Tom Archer (2001) Inside C#, Microsoft Press
- Jeffery Richter (2002) Applied Microsoft .NET Framework Programming, Microsoft Press
- Charles Peltzold (2002) Programming Microsoft Windows With C#, Microsoft Press
- Robinson et al (2001) Professional C#, Wrox
- William R. Staneck (1997) Web Publishing Unleashed Professional Reference Edition, Sams.net
- Robert Callan, The Essence Of Neural Networks (1999) Prentice Hall
- Timothy Masters, Practical Neural Network Recipes In C++ (1993) Morgan Kaufmann (Academic Press)
- Melanie Mitchell, An Introduction To Genetic Algorithms (1999) MIT Press
- Joey Rogers, Object-Orientated Neural Networks in C++ (1997) Academic Press
- Simon Haykin Neural Networks A Comprehensive Foundation (1999) Prentice Hall
- Bernd Oestereich (2002) Developing Software With UML Object-Orientated Analysis And Design In Practice, Addison Wesley
- R Beale & T Jackson (1990) Neural Computing An Introduction, Institute Of Physics Publishing.
Special thanks go to anyone involved in TortoiseCVS for version control.
All UML diagrams were generated using Metamill version 2.2.