MATLAB: Why target data is only binary in the pattern recognition (nnstart) ? Deep Learning Toolboxnnstart bold * Best Answer Because the desired output probabilities are 1 for the correct class and 0 for the incorrect classes.Configured correctly, a successful classifier will output unit sum probability estimates with the correct class estimate being the largest.Hope this helps.Thank you for formally accepting my answerGreg Related SolutionsMATLAB: How to train a feedfordward neural network with error weights Use the command window help mse doc mseHope this helps.Thank you for formally accepting my answerGreg MATLAB: How to create a neural network with 1 layer only (no hidden layers) net = fitnet([]); % For regression net = patternnet([]); % For classificationHope this helps.Thank you for formally accepting my answerGreg Related QuestionNeural Network Pattern RecognitionHow to test a trained network with new dataNeural network for pattern recognitionBad classification even after training neural networkAbout neural net fitting (at neural network toolkit)
Best Answer