DArch-class: Class for deep architectures
In darch: Package for Deep Architectures and Restricted Boltzmann Machines

Description Details Slots Author(s) See Also

This class represents a model created, and/or configured, and/or trained with the darch function. It implements deep architectures and provides the ability to train them with a pre training using contrastive divergence and fine tuning with backpropagation, resilient backpropagation and conjugate gradients.

The class inherits all attributes from the class Net. User-relevant slots include stats (training statistics), epochs (numer of epoch this model was trained for), and parameters (all parameters passed to darch as well as internal parameters).

rbmList: A list which contains all RBMs for the pre-training.
layers: A list with the layer information. In the first field are the weights and in the second field is the unit function.
cancel: Boolean value which indicates if the network training is canceled.
cancelMessage: The message when the execution is canceled.
dropoutMasks: List of dropout masks, used internally.
dataSet: DataSet instance.