Provides actions to tune machine learning algorithm hyperparameters for individual or multiple model types
| Action Name | Description |
|---|---|
| modelComposer | Automatically tunes hyperparameters for multiple models types concurrently, with optimal allocations. |
| tuneAll | Automatically tunes hyperparameters for multiple models types concurrently. |
| tuneBnet | Automatically adjusts Bayesian network classifier parameters to tune a model for minimum error |
| tuneDecisionTree | Automatically adjusts decision tree parameters to tune a model for minimum error |
| tuneFactMac | Automatically adjusts factorization machine parameters to tune a model for minimum error |
| tuneForest | Automatically adjusts forest parameters to tune a model for minimum error |
| tuneGlm | Automatically adjusts linear regression parameters to tune a model for minimum error |
| tuneGPClass | Automatically adjusts Gaussian process classification parameters to tune a model for minimum error |
| tuneGPReg | Automatically adjusts Gaussian process regression parameters to tune a model for minimum error |
| tuneGradientBoostTree | Automatically adjusts gradient boosting tree parameters to tune a model for minimum error |
| tuneGraphMultiReg | Automatically adjusts Generalized Linear Multitask Learning technique parameters to tune for best objective metric value |
| tuneLabelSpread | Automatically adjusts Label Spreading technique parameters to tune for best objective metric value |
| tuneLightGradBoost | Automatically adjusts light grad boost parameters to tune a model for minimum error |
| tuneLogistic | Automatically adjusts logistic regression parameters to tune a model for minimum error |
| tuneNeuralNet | Automatically adjusts neural network parameters to tune a model for minimum error |
| tuneRecBpr | Automatically adjusts Bayesian personalized ranking parameters to tune a model for minimum error |
| tuneRecDtos | Automatically adjusts DTOS model parameters to tune a model for minimum error |
| tuneRecKnn | Automatically adjusts KNN model parameters to tune a model for minimum error |
| tuneSvm | Automatically adjusts support vector machine parameters to tune a model for minimum error |
| tuneTsne | Automatically adjusts t-Distributed Stochastic Neighbor Embedding algorithm parameters to tune for minimum loss |