- Accumulate
- Specifies the names of the input table columns that need to be copied from input test table to output.
- OutputProb
- Specifies whether the function outputs the probability for each response. Only applicable if ModelType is Classification.
- Responses
- Specifies the class labels to output probabilities. Only applicable if OutputProb is true. A label must be 0 or 1. If not specified, the function outputs the probability of the predicted response.
- ModelType
- Specify the model type used by TD_SVM to train the dataset. Acceptable values are Regression, Classification.
- Kernel
- Specifies the type of kernel used to create the model. Acceptable values are Linear and RBF.
The value provided to this argument should be the same as value used to generate the model used by the predict. For example, TD_SVM used non-linear kernel (RBF) to generate the model, the TD_SVMPredict should use the same value for kernel.
Default: Linear
- NComponents
- This hyperparameter is only used if the 'Kernel' is set to 'RBF' (non-linear kernel).
The value provided to this argument should be the same as value used to generate the model used by the predict.
Specifies the number of Monte Carlo samples per the original feature. Equals the dimensionality of the computed feature space.
Default: 100