Encog DotNet 1.1 has been released
We just released version 1.1 of Encog for DotNet. This also includes a Workbench that allowed editing of Encog datafiles. This is a major update to the Encog Neural Network and Bot framework. v1.1 adds the Encog workbench, which is a GUI tool that can be used to edit the .EG files that Encog uses to save neural networks and training data. The workbench can be used to construct all neural network types that Encog supports, such as Hopfield, Feedforward, and Self Organizing Maps. Training can also be performed using the workbench. The workbench can generate Java, C# and Visual Basic code for the neural networks that you create. Additionally there have been several bug fixes and enhancements to the core JAR as well.
The DotNet version of Encog is going directly from 0.5 to 1.1, as we are skipping 1.0. More info about the DotNet version of Encog can be found here.
RSS
YouTube
Twitter
Facebook
Comments
multiple sample for one letter
can one letter has more than one sample?
Should work
I have not specifically tried the SOM example using only one letter. I think a feedforward neural network may work out better if you have more than one sample per letter. That way you can specifically tell the network what goes with what, since you would be using supervised training. Probably a good example for me to write at some point soon!