MemBrain Neural Network Editor + Simulator User Forum

vielleicht eine sehr dumme Frage, aber ich habe in der Hilfe keine eindeutige Aussage dazu gefunden: Dumme Fragen gibt es bekanntlich (fast) keine und in diesem Fall ist vielleicht die MemBrain-Hilfe (Abschnitt 'Net Error Calculation') wirklich nicht ganz so explizit, wie sie sein könnte oder sollt...

What I meant was that there is a difference beetwen data when teaching is finished and then you perform ThinkOnLesson. See attached file Many thanks for the data and the clear video! What you can observe here is exactly the effect of the setting 'Use On-The-Fly Net Error Calculation' for the select...

But in case of time invariant networks with no loops, input -> hidden layer 1 -> hidden layer 2 -> output, results should be exactly the same ? Yes, each 'Think On Lesson' and each 'Evaluate Net Error' should produce exactly the same results in this case independently from the fact if 'Reset Net' i...

So how to validate and employ such network ? Since you use a time variant network to predict time series the validation is ideally performed during (i.e. in parallel to) training. Have you worked through the Time Series Prediction Tutorial which is part of the MemBrain examples? The one that uses t...

What you observe is normal behaviour in case you are working with a time variant net. Try the following: From MemBrain's main menu select 'Net' - 'Analyse Net' and take a look at the analysis summary of the net. You will probably find the statement 'The network is time variant'. This means that your...

1) Wenn ich es richtig verstanden habe ist die Begründing "warum" und "wie" das NN zu seiner Lösung gekommen ist, nicht immer unbedingt nachvollziehbar Das ist absolut korrekt, ja. 'Nicht immer' ist sogar untertrieben, man weiß es eigentlich nie. Man verwendet NN zur Prognose ja...

Hallo Johannes, Kann mir ein NN helfen eine solche Problematik zu lösen wenn ich z.B. die Fragestellung habe: Welches ist (unter meinen gegebenen Vorrausetzungen in der Matrix) die schnellste Lösung, welches wäre die kostengünstigste oder die mit dem geringsten Ausfallrisiko? So etwas (jedenfalls im...

Edit: changed the code, now seems to work, but the result I get are not exactly the same, there is a small difference in fraction part. The code looks fine so far and yes, index 0 ist the left most one in the lesson editor. With respect to the differences: Check out the menu option <Code-Generation...

I am aware of IDENTICAl activation function but it works only for inputs from -1 to 1 so it clips below and above values. I can work around by dividing inputs so they are in the range -1 .. 1. You don't have to perform this manually: MemBrain supports the so called 'Normalization' setting for input...

Hi Krzysztof, sorry for the late reply, I didn't receive notification from the board about this post and just stumbled upon it by accident. Sometimes phpBB doesn't work like it should ;-) Can anyone point me in the right direction ? I have data set with (4 inputs and 1 output) x 1500 records. Is it ...