Trainable classifier by Discriminative Restricted Boltzmann Machine
W = DRBMC(A,N,L)
The classifier trains a discriminative Restricted Boltzmann Machine (RBM) on dataset A. The discriminative RBM can be viewed as a logistic regressor with hidden units. The discriminative RBM has N hidden units (default = 5). It is trained with L2 regularisation using regularisation parameter L (default = 0).
New objects are classified in the same way as in a logistic regressor, using a softmax function over the labels.
H. Larochelle and Y. Bengio. Classification using Discriminative Restricted Boltzmann Machines. Proceedings of the 25th International Conference on Machine Learning (ICML), pages 536?543, 2008.