The new stable release of the GPdotNET will be built on .NET 4.0, so the .NET 3.5 will not be supported at all. The reason for that is the compatibility with ParallelFX. From .NET 4.0 ParallelFX is integral part of the .NET 4.0 System namespace.
Some of the new feature:
1. Localization –The application will be localized on English and Bosnian language.
2. Improvements of the selection engine. Current 4 selections (Elite, Rank, Roulette-Wheel and Tournament) are optimized and rewritten.
a. There are 3 new selections:
i. Stochastic Uniform selection SUS
ii. Fitness Uniform Selection Scheme FUSS
iii. Skrgic Selection Scheme SSS
3. Parallel processing is also optimized but it is still not complete.
4. Fitness measure is expanded to over 15 types (similar to GeneExproTools 4.0):
- Absolute Error with Selection Range
- Absolute/Hits
- MSE (mean squared error)
- RMSE (root mean squared error)
- MAE (mean absolute error)
- RSE (relative squared error)
- RRSE (root relative squared error)
- RAE (relative absolute error)
- Relative Error with Selection Range
- Relative/Hits
- rMSE (relative MSE)
- rRMSE (relative RMSE)
- rMAE (relative MAE)
- rRSE (relative RSE)
- rRRSE (relative RRSE)
- rRAE (relative RAE)
- R-square
- Correlation Coefficient
5. Export results to Excel for further analysis
Screenshots:
Figure 1 Dialog for creating a model 1. Data model, 2. Time series model
Figure 2 Excel definition of the function, for Excel result export
Figure 3: 7 Selection methods
Figure 4: Over 15 Fitness type of measures
Figure 5: Export Options
Bahrudin Hrnjica Blog 
Pingback: GPdotNET on .NET 4.0 Client Profile « Bahrudin Hrnjica Blog
Pingback: GPdotNET with new chart control « Bahrudin Hrnjica Blog
It is really amazing what you are doing! Thank you for giving this excellent piece of work to us!
Will there be the possibility of exporting the formulas into Excel? Or into Computer Algebra Systems (like Maxima) for simplifying them? And will you include the possibility of defining your own functions?
Keep up the good work and thank you again!
Thank you for interest in GPdotNET. The new upcoming version will contain export functionality in to excel, by exporting formula and training data together with basic statistic (residual etc..).