Neural Network training doesn't yield good results

1 view (last 30 days)
Hi, I'm trying to use a neural network for a classification problem, but the result of the training produce very bad performance. The classification problem:
  • I have more than 300,000 training samples
  • Each input is a vector of 32 values (real values)
  • Each output is a vector of 32 values (0 or 1)
This is how I train the network:
DNN_SIZE = [1000, 1000];
% Initialize DNN
net = feedforwardnet(DNN_SIZE, 'traingda');
net.performParam.regularization = 0.2;
%Set activation functions
for i=1:length(DNN_SIZE)
net.layers{i}.transferFcn = 'poslin';
net.layers{end}.transferFcn = 'logsig';
net = train(net, train_inputs, train_outputs);
  • Note: I have tried different values for DNN_SIZE including larger and smaller values, for hidden layers and less, but it didn't make a difference.
  • Note 2: I have tried training the same network using a data set from Matlab's examples (simpleclass_dataset) and I still got bad performance.
The performance of the trained network is very bad- Its output is basically 0.5 in every output for every input vector (when the target outputs during training are always 0 or 1). What am I doing wrong, and how can I fix it?
  1 Comment
Walter Roberson
Walter Roberson on 20 Nov 2016
What reason do you have to expect that you can do better than 50 percent?
I could use rand() to create a 300000 by 32 array of coefficients and randomly assign them to targets 0 and 1, but clearly any classification that did better than 50 percent could only do so through overclassification. What evidence is available to you to suggest that your data can do better?

Sign in to comment.

Answers (0)


Find more on Deep Learning Toolbox in Help Center and File Exchange

Community Treasure Hunt

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

Start Hunting!

Translated by