add_sample_class_mlpT_add_sample_class_mlpAddSampleClassMlpAddSampleClassMlpadd_sample_class_mlp (Operator)

Name

add_sample_class_mlpT_add_sample_class_mlpAddSampleClassMlpAddSampleClassMlpadd_sample_class_mlp — Add a training sample to the training data of a multilayer perceptron.

Signature

add_sample_class_mlp( : : MLPHandle, Features, Target : )

Description

add_sample_class_mlpadd_sample_class_mlpAddSampleClassMlpAddSampleClassMlpAddSampleClassMlpadd_sample_class_mlp adds a training sample to the multilayer perceptron (MLP) given by MLPHandleMLPHandleMLPHandleMLPHandleMLPHandlemlphandle. The training sample is given by FeaturesFeaturesFeaturesFeaturesfeaturesfeatures and TargetTargetTargetTargettargettarget. FeaturesFeaturesFeaturesFeaturesfeaturesfeatures is the feature vector of the sample, and consequently must be a real vector of length NumInputNumInputNumInputNumInputnumInputnum_input, as specified in create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpCreateClassMlpcreate_class_mlp. TargetTargetTargetTargettargettarget is the target vector of the sample, which must have the length NumOutputNumOutputNumOutputNumOutputnumOutputnum_output (see create_class_mlpcreate_class_mlpCreateClassMlpCreateClassMlpCreateClassMlpcreate_class_mlp) for all three types of activation functions of the MLP (exception: see below). If the MLP is used for regression (function approximation), i.e., if OutputFunctionOutputFunctionOutputFunctionOutputFunctionoutputFunctionoutput_function = 'linear'"linear""linear""linear""linear""linear", TargetTargetTargetTargettargettarget is the value of the function at the coordinate FeaturesFeaturesFeaturesFeaturesfeaturesfeatures. In this case, TargetTargetTargetTargettargettarget can contain arbitrary real numbers. For OutputFunctionOutputFunctionOutputFunctionOutputFunctionoutputFunctionoutput_function = 'logistic'"logistic""logistic""logistic""logistic""logistic", TargetTargetTargetTargettargettarget can only contain the values 0.0 and 1.0. A value of 1.0 specifies that the attribute in question is present, while a value of 0.0 specifies that the attribute is absent. Because in this case the attributes are independent, arbitrary combinations of 0.0 and 1.0 can be passed. For OutputFunctionOutputFunctionOutputFunctionOutputFunctionoutputFunctionoutput_function = 'softmax'"softmax""softmax""softmax""softmax""softmax", TargetTargetTargetTargettargettarget also can only contain the values 0.0 and 1.0. In contrast to OutputFunctionOutputFunctionOutputFunctionOutputFunctionoutputFunctionoutput_function = 'logistic'"logistic""logistic""logistic""logistic""logistic", the value 1.0 must be present for exactly one element of the tuple TargetTargetTargetTargettargettarget. The location in the tuple designates the class of the sample. For ease of use, a single integer value may be passed if OutputFunctionOutputFunctionOutputFunctionOutputFunctionoutputFunctionoutput_function = 'softmax'"softmax""softmax""softmax""softmax""softmax". This value directly designates the class of the sample, which is counted from 0, i.e., the class must be an integer between 0 and NumOutputNumOutputNumOutputNumOutputnumOutputnum_output - 1. The class is converted to a target vector of length NumOutputNumOutputNumOutputNumOutputnumOutputnum_output internally.

Before the MLP can be trained with train_class_mlptrain_class_mlpTrainClassMlpTrainClassMlpTrainClassMlptrain_class_mlp, all training samples must be added to the MLP with add_sample_class_mlpadd_sample_class_mlpAddSampleClassMlpAddSampleClassMlpAddSampleClassMlpadd_sample_class_mlp.

The number of currently stored training samples can be queried with get_sample_num_class_mlpget_sample_num_class_mlpGetSampleNumClassMlpGetSampleNumClassMlpGetSampleNumClassMlpget_sample_num_class_mlp. Stored training samples can be read out again with get_sample_class_mlpget_sample_class_mlpGetSampleClassMlpGetSampleClassMlpGetSampleClassMlpget_sample_class_mlp.

Normally, it is useful to save the training samples in a file with write_samples_class_mlpwrite_samples_class_mlpWriteSamplesClassMlpWriteSamplesClassMlpWriteSamplesClassMlpwrite_samples_class_mlp to facilitate reusing the samples, and to facilitate that, if necessary, new training samples can be added to the data set, and hence to facilitate that a newly created MLP can be trained anew with the extended data set.

Execution Information

Multithreading type: reentrant (runs in parallel with non-exclusive operators).
Multithreading scope: global (may be called from any thread).
Processed without parallelization.

This operator modifies the state of the following input parameter:

MLPHandleMLPHandleMLPHandleMLPHandleMLPHandlemlphandle

During execution of this operator, access to the value of this parameter must be synchronized if it is used across multiple threads.

Parameters

MLPHandleMLPHandleMLPHandleMLPHandleMLPHandlemlphandle (input_control, state is modified) class_mlp → (handle)

MLP handle.

FeaturesFeaturesFeaturesFeaturesfeaturesfeatures (input_control) real-array → (real)

Feature vector of the training sample to be stored.

TargetTargetTargetTargettargettarget (input_control) number(-array) → (integer / real)

Class or target vector of the training sample to be stored.

Result

If the parameters are valid, the operator add_sample_class_mlpadd_sample_class_mlpAddSampleClassMlpAddSampleClassMlpAddSampleClassMlpadd_sample_class_mlp returns the value TRUE. If necessary, an exception is raised.