MATLAB: Neural Network Pattern Recognition Tool.

Deep Learning Toolboxneural networkpattern recognition

Hi Everyone, I am quite new to neural networks. I have a problem with pattern recognition using Neural Network Pattern Recognition Tool. As it is shown in demos I created 2 data sets in order to perform simple classification task. Firs one (6×90) contains 90 column vectors with 6 shape coefficient each. Second data set – targets (2×90), contains 90 column vectors where each ith column indicates which category the ith shape (it's either circle or triangle) belongs to. I trained the network with default settings and saved my results. And I'm stuck at this point. How to use trained network to, for example, classify one column vector with 6 shape coefficients to one of two classes? I found tried this http://azload.com/artificial-neural-networks-the-tutorial-with-matlab-5768.html but it seems to be inappropriate for linearly nonseparable problems. Any help would be appreciated:) Jacek

Best Answer

I donno if u used nntool during training..Type nntool in command window it wil open nntool dialog box.. U have to import ur network and test data into it.. after u hav imported double click ur network a dialogue box wil open, in it under simulate tab input ur test data and simulate the results now the simulated results will be stored in nntool dialogue box.. u can open it and view the results.. if u want to work with that data u can export it into workspace.. the result is usually a non-integer you can use round command to round it to the nearest integer.. hope this is useful :)
Related Question