backpropagate.adapt.R.neuron: Backpropagates the single pattern error modifying accordingly the neuron's weights and bias.
Description
This is the original R code version mainly written to be called by backpropagate.adapt.R.NeuralNet. Since this latter function has been rewritten (backpropagate.adapt.C.NeuralNet) to call the C code corresponding function (BackpropagateAdaptNeuronC), it has been kept just for educational purposes and it is not meant to be used otherwise.
Usage
backpropagate.adapt.R.neuron(net, ind.neuron)
Arguments
net
Neural Network to train.
ind.neuron
Index of the neuron that needs to suffer the backpropagation effect.
Value
This function returns a neuron object with weights and bias adjusted by the adaptative backpropagation with momentum method.
encoding
latin1
References
Simon Haykin. Neural Networks. A comprehensive foundation. 2nd Edition.