Use of Validation data with Sequential Network Construction

[pvareschi]

Re: Neural Network Modelling

Is it possible to use Validation data with Sequential Network Construction (page 4.35 of course text)? i.e. use performance on Validation data to inform when to stop adding nodes?

[zhongxiuliu · Accepted solution]

that's a good approach to implement. 

For small neural network on data with well-defined features (often <=2 layers), I wouldn't go through the effort of sequential network construction. 

SAS Viya's PROC NNET auto-tuning is a better approach. With deep learning (deeplearn casl action set), drop-out is a also another better approach. You can look into both through online documentation.