MATLAB: Neural Network Pattern Recognition

neural networkstarget data

Hi all,

I want to train a neural network pattern recognition, I use command "Patternnet" to create the network and command "train" for training. my problem is that I don't know how to creat my target data.

I have 12000 pictures for trainig each 28*28 size which belong to 5 classes. I normalized my input data so I have a input matrix of 12000*784 ranging between 0 and 1.

Can you pleas tell me how can I impeliment my target data for this network?

I face this error!

"Error using network/train (line 340)

Inputs and targets have different numbers of samples."

Best Answer

Targets are 1-dimensional unit vectors with 4 zeros and a single 1 .

Thank you for formally accepting my answer.

Greg

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: Normalize Inputs and Targets of neural network

MAPMINMAX can be inappropriate only if there are outliers.

Use MAPSTD to detect outliers that can be removed or modified.

Hope this helps.

Thank you for formally accepting my answer

Greg

Related Question