Skip to content

evaluate_class_mlpEvaluateClassMlpEvaluateClassMlpevaluate_class_mlpT_evaluate_class_mlpđź”—

Short descriptionđź”—

evaluate_class_mlpEvaluateClassMlpEvaluateClassMlpevaluate_class_mlpT_evaluate_class_mlp — Calculate the evaluation of a feature vector by a multilayer perceptron.

Signatuređź”—

evaluate_class_mlp( class_mlp MLPHandle, real Features, out real Result )void EvaluateClassMlp( const HTuple& MLPHandle, const HTuple& Features, HTuple* Result )static void HOperatorSet.EvaluateClassMlp( HTuple MLPHandle, HTuple features, out HTuple result )def evaluate_class_mlp( mlphandle: HHandle, features: Sequence[float] ) -> Sequence[float]

Herror T_evaluate_class_mlp( const Htuple MLPHandle, const Htuple Features, Htuple* Result )

HTuple HClassMlp::EvaluateClassMlp( const HTuple& Features ) const

HTuple HClassMlp.EvaluateClassMlp( HTuple features )

Descriptionđź”—

evaluate_class_mlpEvaluateClassMlp computes the result Resultresultresult of evaluating the feature vector Featuresfeaturesfeatures with the multilayer perceptron (MLP) MLPHandleMLPHandlemlphandle. The formulas used for the evaluation are described with create_class_mlpCreateClassMlp. Before calling evaluate_class_mlpEvaluateClassMlp, the MLP must be trained with train_class_mlpTrainClassMlp.

If the MLP is used for regression (function approximation), i.e., if (OutputFunctionoutputFunctionoutput_function \(=\) 'linear'"linear"), Resultresultresult is the value of the function at the coordinate Featuresfeaturesfeatures. For OutputFunctionoutputFunctionoutput_function \(=\) 'logistic'"logistic" and 'softmax'"softmax", the values in Resultresultresult can be interpreted as probabilities. Hence, for OutputFunctionoutputFunctionoutput_function \(=\) 'logistic'"logistic" the elements of Resultresultresult represent the probabilities of the presence of the respective independent attributes. Typically, a threshold of 0.5 is used to decide whether the attribute is present or not. Depending on the application, other thresholds may be used as well. For OutputFunctionoutputFunctionoutput_function \(=\) 'softmax'"softmax" usually the position of the maximum value of Resultresultresult is interpreted as the class of the feature vector, and the corresponding value as the probability of the class. In this case, classify_class_mlpClassifyClassMlp should be used instead of evaluate_class_mlpEvaluateClassMlp because classify_class_mlpClassifyClassMlp directly returns the class and corresponding probability.

Execution informationđź”—

Execution information

  • Multithreading type: reentrant (runs in parallel with non-exclusive operators).

  • Multithreading scope: global (may be called from any thread).

  • Processed without parallelization.

Parametersđź”—

MLPHandleMLPHandlemlphandle (input_control) class_mlp → (handle)HTuple (HHandle)HClassMlp, HTuple (IntPtr)HHandleHtuple (handle)

MLP handle.

Featuresfeaturesfeatures (input_control) real-array → (real)HTuple (double)HTuple (double)Sequence[float]Htuple (double)

Feature vector.

Resultresultresult (output_control) real-array → (real)HTuple (double)HTuple (double)Sequence[float]Htuple (double)

Result of evaluating the feature vector with the MLP.

Resultđź”—

If the parameters are valid, the operator evaluate_class_mlpEvaluateClassMlp returns the value 2 (H_MSG_TRUE). If necessary, an exception is raised.

Combinations with other operatorsđź”—

Combinations

Possible predecessors

train_class_mlpTrainClassMlp, read_class_mlpReadClassMlp

Alternatives

classify_class_mlpClassifyClassMlp

See also

create_class_mlpCreateClassMlp

Referencesđź”—

Christopher M. Bishop: “Neural Networks for Pattern Recognition”; Oxford University Press, Oxford; 1995.

Andrew Webb: “Statistical Pattern Recognition”; Arnold, London; 1999.

Moduleđź”—

Foundation