C++ API Reference for Intel® Data Analytics Acceleration Library 2020 Update 1
LogitBoost algorithm parameters. More...
DAAL_DEPRECATED Parameter | ( | ) |
Default constructor
DAAL_DEPRECATED Parameter | ( | const services::SharedPtr< weak_learner::training::Batch > & | wlTrainForParameter, |
const services::SharedPtr< weak_learner::prediction::Batch > & | wlPredictForParameter, | ||
double | acc = 0.0 , |
||
size_t | maxIter = 10 , |
||
size_t | nC = 0 , |
||
double | wThr = 1e-10 , |
||
double | zThr = 1e-10 |
||
) |
Constructs LogitBoost parameter structure
[in] | wlTrainForParameter | Pointer to the training algorithm of the weak learner |
[in] | wlPredictForParameter | Pointer to the prediction algorithm of the weak learner |
[in] | acc | Accuracy of the LogitBoost training algorithm |
[in] | maxIter | Maximal number of terms in additive regression |
[in] | nC | Number of classes in the training data set |
[in] | wThr | Threshold to avoid degenerate cases when calculating weights W |
[in] | zThr | Threshold to avoid degenerate cases when calculating responses Z |
double accuracyThreshold |
Accuracy of the LogitBoost training algorithm
size_t maxIterations |
Maximal number of terms in additive regression
size_t nClasses |
Number of classes
double responsesDegenerateCasesThreshold |
Threshold to avoid degenerate cases when calculating responses Z
double weightsDegenerateCasesThreshold |
Threshold to avoid degenerate cases when calculating weights W
For more complete information about compiler optimizations, see our Optimization Notice.