MATLAB: Train Recgnition Neural Network on image moements

Deep Learning Toolboximage momentsimage processingneural networkpattern recognition

I am trying to train pattern recognition neural network on set of image moments values, when trying to simulate i keep getting the same result for every input, tried to normalize the data using "mapminmax" but still no luck

P.S the seven moments contain negative numbers

Best Answer

Mapminmax is a default.

What did you get for performance?

You may have converged to a local min.

Repeat 9 more times with different random initial weights.

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 train ann with multiple input data

% Create a network (i have used feed-forward backpropagation)
net = newff(TrainFeatures, Trainlabels, num_of_hidden_Neurons);
% Set Train, Test and Validation Ration
net.divideParam.trainRatio = 70/100;  
net.divideParam.valRatio = 15/100;  
net.divideParam.testRatio = 15/100; 
net = train(net, TrainFeatures, Trainlabels);

Best Answer

Related Solutions

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

MATLAB: How to train ann with multiple input data

Related Question