This function provides the backpropagation algorithm for deep architectures.
backpropagation(darch, trainData, targetData, ...)The data for training.
The targets for the data.
Further parameters.
The trained deep architecture
The function is getting the learning parameters from the provided
'>DArch object. It uses the attributes momentum,
finalMomentum and momentumSwitch for the calculation of the new
weights with momentum. The attributes learnRateWeights and
learnRateBiases will be used for updating the weights. To use the
backpropagation function as the fine tuning function the layer functions of
the darch '>DArch object must set to the versions which
calculates also the derivatives of the function result.
Rumelhart, D., G. E. Hinton, R. J. Williams, Learning representations by backpropagating errors, Nature 323, S. 533-536, DOI: 10.1038/323533a0, 1986.
'>DArch, rpropagation,
minimizeAutoencoder minimizeClassifier
minimizeClassifier
Other fine-tuning functions: rpropagation