What are the extra return values of this Neural Network training code?

Hello there, i'm analyzing a multilayer perceptron code and cant find what are the extra return values of the train function.

[net,tr,Y,E] = train(net,P,T);

where: net = Feedforward Network. P = inputs array. T = targets array.

Thanks.

Answer 1

[Greg Heath]

For regression/curve-fitting (e.g., FITNET) and classification/pattern-recognition (e.g., PATTERNNET) with double variables

 [ net tr y e ] = train( net, x, t );

 % net - trained net
 % tr  - training record
 % y   - output y= net( x )
 % e   - error  e = t - y

 tr = tr   % Command to divulge contents (NO SEMICOLON)

For time-series (e.g., TIMEDELAYNET, NARNET, NARXNET), with cell variables

 [ neto tro Yo Eo Xof Aof ] = train( neto, Xo, To, Xoi, Aoi );

 % o    - openloop subscript
 % Xoi  - initial input delay state
 % Aoi  - initial output feedback delay state
 % neto - trained openloop net
 % tro  - training record
 % Yo   - output Yo = net( Xo, Xoi, Aoi)
 % Eo   - error  Eo = gsubtract( To , Yo)
 % Xof  - final input delay state
 % Aof  - final output delay state [ Yo Xof Aof ] = net( Xo, Xoi, Aoi)

Hope this helps.

THANK YOU FOR FORMALLY ACCEPTING MY ANSWER

Greg

[Marco castillo]

Thank you so much for your answer, it is very clear.