error: [inputValues, targetValues] = input_preprocess();
显示 更早的评论
[inputValues, targetValues] = input_preprocess(); % Transform the labels to correct target values.
% Choose form of MLP:
numberOfHiddenUnits = 1250;
% Choose appropriate parameters.
learningRate = 0.1;
% Choose activation function.
activationFunction = @logisticSigmoid;
dActivationFunction = @dLogisticSigmoid;
% Choose batch size and epochs. Remember there are 60k input values.
batchSize = 20;
epochs = 10000;
fprintf('Train twolayer perceptron with %d hidden units.\n', numberOfHiddenUnits);
fprintf('Learning rate: %d.\n', learningRate);
[hiddenWeights, outputWeights, error] = train(activationFunction, dActivationFunction, numberOfHiddenUnits, inputValues, targetValues, epochs, batchSize, learningRate);
save Train.mat hiddenWeights outputWeights
回答（0 个）
类别
在 帮助中心 和 File Exchange 中查找有关 Pattern Recognition and Classification 的更多信息
2018-3-12
2018-3-12
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!
Translated by 
