Need advice for approach for multivariate regression/prediction using Deep Networks

I am trying to build predictive models for 2 outputs given approximately 10 input variables.

I understand that I would first look at the simplest model, such as a multivariate linear regression, then to build neural networks (e.g. 1 hidden layer) and progressively move on to deeper hierarchies.

I have 2 questions:

1) Consider the 3 neural network architectures below: Each model attempts to predict 2 outputs given a bunch of predictors (input, independent variables). Which would be ideal?

2) How do I decide on which is the best neural network? I have currently performed NetTrain[] on my data and am curious how to evaluate performance metrics within Mathematica.

Regards

• You already mentioned yourself that with only 10 inputs and 2 outputs (that I assume are scalar values) your problem is not a good fit for neural networks. If you really really really want to use a neural network use the simplest archicture possible, use regularization and you better have a large amount of training data as weil – Sascha Aug 4 '17 at 5:53
• Please give a dateset and net code to test. – HyperGroups Aug 4 '17 at 6:23

Normally by using a validation set (NetTrain can do that for you) to see how well it generalizes to unknown data.