This function is to construct a residual autoencoder-based deep network.
AutoEncoderModel(nfea, nout, nodes, acts, mdropout = 0, reg = NULL,
batchnorm = TRUE, isres = TRUE, outtype = 0, fact = "linear")integer, Number of features
integer, Number of output units
list of integers, list of the number of nodes for the hidden layers in encoding component
list of strings, list of activation function names
double, dropout rate of the coding (middle) layer (default:0)
string, regularization string (default: NULL)
bool, flag to conduct batch normalization (default:TRUE)
bool, flag to conduct the residual connections (default: TRUE)
integer, output type, 0 indicating nout outputs and 1 nout+nfea outputs (default: 0)
string, activation for output layer (default:"linear")
keras model, model of (residual) autoencoder-based deep network