Can't get neural network result in MATLAB -
i guess question simple, anyway...
i've created neural network using
net = newff(entry_borders, [20, 10], {'logsig', 'logsig'}, 'traingdx');
where entry_borders array 50x2: [(0,1), (0,1), ...]
it must network hidden layer 50 entries , 10 outputs, isn't it?
but when run this:
test_result = sim(net, zeros(50)); disp(test_result);
i matrix 10x50 elements in test_result (instead of 10 scalar values) - what's that?? i'm not speaking teaching process that's why here's sily code...
zeros(50)
gives 50x50 matrix, treated 50 examples (each of dimension 50), gives 50 predictions (each of size 10)
Comments
Post a Comment