Azzera filtri
Azzera filtri

Hi . I am new to DNN. I use deep neural network for binary classification but returns all zeros or ones.

16 visualizzazioni (ultimi 30 giorni)
I've tried using machine learning approach(SVM, KNN, Tree...) and the accuracy is good.
I am interested in transfer learning so I want to build a deep learning model.
The attached picture is my training data, column 1 to 9 are features and the marked column(10) is the response which will be changed into categorical vector for training.
And here's my code for network training.
And my data for training is attached ༼ •̀ ں •́ ༽ Thanks
layers = [
options = trainingOptions('adam', ...
'InitialLearnRate',0.01, ...
'MaxEpochs',30, ...
'ValidationData',{xtest,ytest}, ...
'ValidationFrequency',3, ...
'MiniBatchSize',1024, ...
'Verbose',1, ...
  4 Commenti
Tommy Bear
Tommy Bear il 21 Feb 2020
Yeah the accuracy is bad since the responses are all the same(ones) for arbitrary predictors.

Accedi per commentare.

Risposta accettata

Daniel Vieira
Daniel Vieira il 21 Feb 2020
I recommend normalizing your predictors, they range from 10^-5 to 10^9, pretty insane. I'd rather work with the log10 of that (ranging from -5 to 9).
I would also change the sequence input layer to an imageInputLayer with size [1 9], and possibly adapt the way you give the input data. The sequence input layer is meant for the LSTM model, not your case. The imageInputLayer, although meant for images, works just fine with vectors and matrices of any sort.
  3 Commenti
Tommy Bear
Tommy Bear il 25 Feb 2020
Oh seems my validation data was wrong dimension and I fixed it.
But the accuracy won't improve as long as reach around 80%, any suggestion for improving results?
Daniel Vieira
Daniel Vieira il 26 Feb 2020
it may be because your data is unbalanced, like Srivardhan Gadila said below. When it's too unbalanced, the network will nearly always answer in favor of the most frequent label, effectively "capping" accuracy, and mistaking all the less frequent labels. You should select equal (or nearly equal) ammounts of observations for each label. It should improve your accuracy.

Accedi per commentare.

Più risposte (1)

Srivardhan Gadila
Srivardhan Gadila il 25 Feb 2020
Seems that your dataset is unbalanced, count of sequences with label 0 is 59695 and with label 1 is 94226. This could make the learning of the network biased to label 1. Please refer to Prepare and Preprocess Data & Deep Learning Tips and Tricks for more information.
For normalization of data you can make use of the of 'Normalization' & 'NormalizationDimension' Name-Value pair arguments of the sequenceInputLayer or imageInputLayer.




Community Treasure Hunt

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

Start Hunting!

Translated by