MATLAB: How to overcome poor prediction of neural network.

Deep Learning Toolboxfittingneural networkneural networks

I have created a neural network with nftool for prediction with default settings. Data used for input is matrix of 19×1140 i.e 19 input parameter and 1×1140 i.e 1 output parameter. The regression values comes around .99 and .98 but during prediction using sim(net,test) command it gives wrong prediction. How to solve this problem?

Best Answer

Use datadivision and as few hidden nodes as possible. Repeat multiple times to get a good set of random initial weights.

What do you mean by prediction ... the test set performance?

Related Solutions

MATLAB: How to train a feedfordward neural network with error weights

 Use the command window
 help mse
 doc mse

Hope this helps.

Thank you for formally accepting my answer

Greg

MATLAB: How to create a neural network with 1 layer only (no hidden layers)

 net = fitnet([]);     % For regression
 net = patternnet([]); % For classification