You can basically export most of the Neural Network models you build using the R nnet package into PMML by using the PMML package is available from CRAN. With this package, a PMML representation can be obtained for Neural Networks implementing:
- multi-class classification
- binary classifcation
- Scaling of input variables: Since nnet does not automatically implement scaling of numerical inputs, you will need to add scaling via the pmmlTransformations package pass that computation to the pmml package together with the nnet object. You will need to do that if you are planning to use the model to compute scores/results from raw data.
- The PMML exporter uses transformations to create dummy variables for categorical inputs. These are expressed in the NeuralInputs element of the resulting PMML file.
- PMML does not support the censored variant of softmax.
- Given that nnet uses a single output node to represent binary classification, the resulting PMML file contains a discretizer with a threshold set to 0.5.