Understand number of weights of Neural Network

8 Ansichten (letzte 30 Tage)
Joel am 24 Jan. 2018
Beantwortet: Greg Heath am 23 Aug. 2019
I have a Mx120 validation dataset (A), and a Nx120 training dataset (B).
The results look promising, but I am struggling to understand how the weights relate to the training dataset.
using the following code
A = xlsread('Validation.csv');
B = xlsread('Training.csv');
net = fitnet([]);
% Setup Division of Data for Training, Validation, Testing
net.divideFcn = 'dividerand'; % Divide data randomly
net.divideMode = 'sample'; % Divide up every sample
net.divideParam.trainRatio = 70/100;
net.divideParam.valRatio = 15/100;
net.divideParam.testRatio = 15/100;
% Train the Network
[net, tr] = train(net, B, A);
And the following line to inspect the weights
% View the weights
I see that the number of weights are N-1 - i.e. the number of variables in the training dataset minus one.
What I would like to be able to do is to understand the relative importance of each of the variables in the training dataset. Is this possible?
Apologies if this has been asked before. I did not manage to find a matching answer, but may very well have missed something. If so, please do point me in the right direction.
Thank you in anticipation.

Akzeptierte Antwort

Greg Heath
Greg Heath am 25 Jan. 2018
Bearbeitet: Greg Heath am 25 Jan. 2018
You do not understand MANY fundamental concepts.
1. [ trainednet, trainingrecord] = train(untrainednet, input, target)
target = desiredoutput
2. output = trainednet(input);
3. error = target - output;
4. input, target, output and error with length N are all divided into 3 INTERMINGLED parts: TRAINING, VALIDATION AND TESTING with number of points Ntrn, Nval and Ntst ,respectively with
N = Ntrn + Nval + Ntst
5. a. trn used to calculate weights
b. val used to stop training when val error
OF EPOCHS (eg, 5)
c. tst used to obtain an unbiased
(i.e., nondesign) error estimate
Hope this helps.
Thank you for formally accepting my answer
  1 Kommentar
Joel am 26 Jan. 2018
Thanks for the thorough explanation, Greg. I appreciate it! I clearly need to read up more about especially point 4.
Thanks again.

Melden Sie sich an, um zu kommentieren.

Weitere Antworten (2)

Ali sameer
Ali sameer am 17 Aug. 2019
Bearbeitet: Ali sameer am 18 Aug. 2019
Dear sir ;
the first step in ANN in matlab toolbox is to sellect the weights and baises ranomly then it is going to correct these values.
Is it possible to manually enter the initial values to ANN rather than it automatically selects these values randomly and then train the ANN based on selected weights and baises

Greg Heath
Greg Heath am 23 Aug. 2019
It is possible.
In general, however, you don't have the slightest idea what choice would be significantly better than random.
Moreover, the number of successful random initializations is, typically, infinite.
Furthermore, it is much easier to train 10 randomly initialized nets ON TRAINING DATA and choose the one with the BEST VALIDATION PERFORMANCE in order to get an UNBIASED ESTIMATE of the best performing net on unseen (e.g., TEST) data.
Hope this helps.
*THANK YOU for formally accepting my answer!


Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by