read_samples_class_mlp — Read the training data of a multilayer perceptron from a file.
read_samples_class_mlp reads training samples from the file
FileName and adds them to the training samples
that have already been added to the multilayer perceptron (MLP)
MLPHandle. The MLP must be created with
create_class_mlp before calling
read_samples_class_mlp. As described with
can be used to build up a extensive set of training samples, and
hence to improve the performance of the MLP by retraining the MLP
with extended data sets.
It should be noted that the training samples must have the correct
dimensionality. The feature vectors and target vectors stored in
FileName must have the lengths
NumOutput that were specified with
create_class_mlp. If this is not the case an error message
This operator modifies the state of the following input parameter:
During execution of this operator, access to the value of this parameter must be synchronized if it is used across multiple threads.
MLPHandle(input_control, state is modified) class_mlp
If the parameters are valid, the operator
read_samples_class_mlp returns the value 2 (H_MSG_TRUE). If necessary,
an exception is raised.