ml

ml_VAR_NUMERICAL: same as VAR_ORDERED
ml_VAR_ORDERED: ordered variables
ml_VAR_CATEGORICAL: categorical variables
ml_TEST_ERROR: ml test error constant (0), defined by OpenCV for cv::ml.
ml_TRAIN_ERROR: ml train error constant (1), defined by OpenCV for cv::ml.
ml_ROW_SAMPLE: each training sample is a row of samples
ml_COL_SAMPLE: each training sample occupies a column of samples
ml_StatModel_UPDATE_MODEL: ml stat model update model constant (1), defined by OpenCV for cv::ml::StatModel.
ml_STAT_MODEL_UPDATE_MODEL: ml stat model update model constant (1), defined by OpenCV for cv::ml::StatModel.
ml_StatModel_RAW_OUTPUT: makes the method return the raw results (the sum), not the class label
ml_STAT_MODEL_RAW_OUTPUT: makes the method return the raw results (the sum), not the class label
ml_StatModel_COMPRESSED_INPUT: makes the method return the raw results (the sum), not the class label
ml_STAT_MODEL_COMPRESSED_INPUT: makes the method return the raw results (the sum), not the class label
ml_StatModel_PREPROCESSED_INPUT: ml stat model preprocessed input constant (4), defined by OpenCV for cv::ml::StatModel.
ml_STAT_MODEL_PREPROCESSED_INPUT: ml stat model preprocessed input constant (4), defined by OpenCV for cv::ml::StatModel.
ml_KNearest_BRUTE_FORCE: ml knearest brute force constant (1), defined by OpenCV for cv::ml::KNearest.
ml_KNEAREST_BRUTE_FORCE: ml knearest brute force constant (1), defined by OpenCV for cv::ml::KNearest.
ml_KNearest_KDTREE: ml knearest kdtree constant (2), defined by OpenCV for cv::ml::KNearest.
ml_KNEAREST_KDTREE: ml knearest kdtree constant (2), defined by OpenCV for cv::ml::KNearest.
ml_SVM_C_SVC: C-Support Vector Classification. n-class classification (n \geq 2), allows imperfect separation of classes with penalty multiplier C for outliers.
ml_SVM_NU_SVC: \nu-Support Vector Classification. n-class classification with possible imperfect separation. Parameter \nu (in the range 0..1, the larger the value, the smoother the decision boundary) is used instead of C.
ml_SVM_ONE_CLASS: Distribution Estimation (One-class %SVM). All the training data are from the same class, %SVM builds a boundary that separates the class from the rest of the feature space.
ml_SVM_EPS_SVR: \epsilon-Support Vector Regression. The distance between feature vectors from the training set and the fitting hyper-plane must be less than p. For outliers the penalty multiplier C is used.
ml_SVM_NU_SVR: \nu-Support Vector Regression. \nu is used instead of p. See [LibSVM] for details.
ml_SVM_CUSTOM: Returned by SVM::getKernelType in case when custom kernel has been set
ml_SVM_LINEAR: Linear kernel. No mapping is done, linear discrimination (or regression) is done in the original feature space. It is the fastest option. K(x_i, x_j) = x_i^T x_j.
ml_SVM_POLY: Polynomial kernel: K(x_i, x_j) = (\gamma x_i^T x_j + coef0)^{degree}, \gamma > 0.
ml_SVM_RBF: Exponential Chi2 kernel, similar to the RBF kernel:
ml_SVM_SIGMOID: Sigmoid kernel: K(x_i, x_j) = \tanh(\gamma x_i^T x_j + coef0).
ml_SVM_CHI2: Exponential Chi2 kernel, similar to the RBF kernel: K(x_i, x_j) = e^{-\gamma \chi^2(x_i,x_j)}, \chi^2(x_i,x_j) = (x_i-x_j)^2/(x_i+x_j), \gamma > 0.
ml_SVM_INTER: Histogram intersection kernel. A fast kernel. K(x_i, x_j) = min(x_i,x_j).
ml_SVM_C: ml svm c constant (0), defined by OpenCV for cv::ml::SVM.
ml_SVM_GAMMA: ml svm gamma constant (1), defined by OpenCV for cv::ml::SVM.
ml_SVM_P: ml svm p constant (2), defined by OpenCV for cv::ml::SVM.
ml_SVM_NU: ml svm nu constant (3), defined by OpenCV for cv::ml::SVM.
ml_SVM_COEF: ml svm coef constant (4), defined by OpenCV for cv::ml::SVM.
ml_SVM_DEGREE: ml svm degree constant (5), defined by OpenCV for cv::ml::SVM.
ml_EM_COV_MAT_SPHERICAL: A scaled identity matrix \mu_k * I. There is the only parameter \mu_k to be estimated for each matrix. The option may be used in special cases, when the constraint is relevant, or as a first step in the optimization (for example in case when the data is preprocessed with PCA). The results of such preliminary estimation may be passed again to the optimization procedure, this time with covMatType=EM::COV_MAT_DIAGONAL.
ml_EM_COV_MAT_DIAGONAL: A symmetric positively defined matrix. The number of free
ml_EM_COV_MAT_GENERIC: A symmetric positively defined matrix. The number of free parameters in each matrix is about d^2/2. It is not recommended to use this option, unless there is pretty accurate initial estimation of the parameters and/or a huge number of training samples.
ml_EM_COV_MAT_DEFAULT: ml em cov mat default constant (COV_MAT_DIAGONAL), defined by OpenCV for cv::ml::EM.
ml_EM_DEFAULT_NCLUSTERS: Default parameters
ml_EM_DEFAULT_MAX_ITERS: Default parameters
ml_EM_START_E_STEP: The initial step
ml_EM_START_M_STEP: The initial step
ml_EM_START_AUTO_STEP: The initial step
ml_DTrees_PREDICT_AUTO: Predict options
ml_DTREES_PREDICT_AUTO: Predict options
ml_DTrees_PREDICT_SUM: Predict options
ml_DTREES_PREDICT_SUM: Predict options
ml_DTrees_PREDICT_MAX_VOTE: Predict options
ml_DTREES_PREDICT_MAX_VOTE: Predict options
ml_DTrees_PREDICT_MASK: Predict options
ml_DTREES_PREDICT_MASK: Predict options
ml_Boost_DISCRETE: Discrete AdaBoost.
ml_BOOST_DISCRETE: Discrete AdaBoost.
ml_Boost_REAL: Real AdaBoost. It is a technique that utilizes confidence-rated predictions
ml_BOOST_REAL: Real AdaBoost. It is a technique that utilizes confidence-rated predictions
ml_Boost_LOGIT: LogitBoost. It can produce good regression fits.
ml_BOOST_LOGIT: LogitBoost. It can produce good regression fits.
ml_Boost_GENTLE: Gentle AdaBoost. It puts less weight on outlier data points and for that
ml_BOOST_GENTLE: Gentle AdaBoost. It puts less weight on outlier data points and for that
ml_ANN_MLP_BACKPROP: The back-propagation algorithm.
ml_ANN_MLP_RPROP: The RPROP algorithm. See [RPROP93] for details.
ml_ANN_MLP_ANNEAL: The simulated annealing algorithm. See [Kirkpatrick83] for details.
ml_ANN_MLP_IDENTITY: Identity function: f(x)=x
ml_ANN_MLP_SIGMOID_SYM: Symmetrical sigmoid: f(x)=\beta*(1-e^{-\alpha x})/(1+e^{-\alpha x})

Note: If you are using the default sigmoid activation function with the default parameter values fparam1=0 and fparam2=0 then the function used is y = 1.7159*tanh(2/3 * x), so the output will range from [-1.7159, 1.7159], instead of [0,1].
ml_ANN_MLP_GAUSSIAN: Gaussian function: f(x)=\beta e^{-\alpha x*x}
ml_ANN_MLP_RELU: ReLU function: f(x)=max(0,x)
ml_ANN_MLP_LEAKYRELU: Leaky ReLU function: for x>0 f(x)=x and x<=0 f(x)=\alpha x
ml_ANN_MLP_UPDATE_WEIGHTS: Update the network weights, rather than compute them from scratch. In the latter case the weights are initialized using the Nguyen-Widrow algorithm.
ml_ANN_MLP_NO_INPUT_SCALE: Do not normalize the input vectors. If this flag is not set, the training algorithm normalizes each input feature independently, shifting its mean value to 0 and making the standard deviation equal to 1. If the network is assumed to be updated frequently, the new training data could be much different from original one. In this case, you should take care of proper normalization.
ml_ANN_MLP_NO_OUTPUT_SCALE: Do not normalize the output vectors. If the flag is not set, the training algorithm normalizes each output feature independently, by transforming it to the certain range depending on the used activation function.
ml_LogisticRegression_REG_DISABLE: Regularization disabled
ml_LOGISTIC_REGRESSION_REG_DISABLE: Regularization disabled
ml_LogisticRegression_REG_L1: ml_LogisticRegression_REG_L1: %L1 norm
ml_LOGISTIC_REGRESSION_REG_L1: ml_LOGISTIC_REGRESSION_REG_L1: %L1 norm
ml_LogisticRegression_REG_L2: ml_LogisticRegression_REG_L2: %L2 norm
ml_LOGISTIC_REGRESSION_REG_L2: ml_LOGISTIC_REGRESSION_REG_L2: %L2 norm
ml_LogisticRegression_BATCH: ml logistic regression batch constant (0), defined by OpenCV for cv::ml::LogisticRegression.
ml_LOGISTIC_REGRESSION_BATCH: ml logistic regression batch constant (0), defined by OpenCV for cv::ml::LogisticRegression.
ml_LogisticRegression_MINI_BATCH: Set MiniBatchSize to a positive integer when using this method.
ml_LOGISTIC_REGRESSION_MINI_BATCH: Set MiniBatchSize to a positive integer when using this method.
ml_SVMSGD_SGD: Stochastic Gradient Descent
ml_SVMSGD_ASGD: Average Stochastic Gradient Descent
ml_SVMSGD_SOFT_MARGIN: General case, suits to the case of non-linearly separable sets, allows outliers.
ml_SVMSGD_HARD_MARGIN: More accurate for the case of linearly separable sets.