Use of nominal and ordinal inputs in GANN

[pvareschi]

Re: Neural Network Modelling

Based on statement at the bottom of page 4-56 of the course text, nominal and ordinal inputs cannot be assessed by using partial residual plots when building a GANN (generalised additive neural network): can they be used in a GANN at all? And, would that include binary inputs too?

[zhongxiuliu · Accepted solution]

GANN is just like other neural network except that there's a direct connection between input and output (some people call it skipped layer neural network). So nominal and ordinal be encoded into numerical values and used just like in other neural networks.
that would include binary inputs too