OK, so I guess I must be the only one using the NEURAL functions. I've solved the naming problem above with a little help from Zorro support (thanks!). However, I've struck another obstacle to using NEURAL within an asset loop.

The manual states that NEURAL_TRAIN, NEURAL_SAVE and NERUAL_LOAD are each called only at the end of a WFO cycle. This is fine, but the result is that when called in an asset loop, these functions are executed for the final asset in the loop only.

Is there a workaround, or something that I'm missing, that would enable me to use these functions in an asset loop?

Thanks