I would like to know if there is a way to find the best values for the parameters theta minus and theta plus, on the configuration of the Probabilistic Neural Network (PNN Learner (DDA) Node). Is there any heuristic? Thanks in advance.
I'm no expert in PNNs but have a look at our example server under 011_FlowVarsAndLoops/011003_loopParametersKMeans
This workflow shows you how to set up a loop to find better (if not the best), parameters for your model. If there are any other approaches that might be useful we will have to see if someone else in the community can point us at them.
I found your post and wish to know about your advances on this theme since then. I am currently facing similar problems with both Theta parameters. Would you mind updating me after such a long interval?