Program sfonelayer | One layer NN training.
[SYNOPSIS]
sfonelayer < x_train_obj.rsf ytrain=y_train_obj.rsf xval=x_val_obj.rsf yval=y_val_obj.rsf > loss_train_obj.rsf lossval=loss_val_obj.rsf
[COMMENTS]

Reproducing the training process of the following example:
https://github.com/seg/tutorials-2018/tree/master/1808_Neural_networks
This is a minimal one-layer network:
x -> a -> z == y
The training uses L2 loss function.

[PARAMETERS]
file    | lossval | = |   | 	auxiliary output file name
file    | xval | = |   | 	auxiliary input file name
file    | ytrain | = |   | 	auxiliary input file name
file    | yval | = |   | 	auxiliary input file name
[DIRECTORY]
user/fomels
