Optimized algorithms to solve specialized unsupervised optimization problems.
A supervised problem consists only of input data. Typical tasks are normalization distribution learning
Classes | |
| class | shark::AbstractUnsupervisedTrainer< Model > |
| Superclass of unsupervised learning algorithms. More... | |
| class | shark::AbstractWeightedUnsupervisedTrainer< Model > |
| Superclass of weighted unsupervised learning algorithms. More... | |
| class | shark::NormalizeComponentsUnitInterval< DataType > |
| Train a model to normalize the components of a dataset to fit into the unit inverval. More... | |
| class | shark::NormalizeComponentsUnitVariance< DataType > |
| Train a linear model to normalize the components of a dataset to unit variance, and optionally to zero mean. More... | |
| class | shark::NormalizeComponentsWhitening |
| Train a linear model to whiten the data. More... | |
| class | shark::NormalizeComponentsZCA |
| Train a linear model to whiten the data. More... | |
| class | shark::NormalizeKernelUnitVariance< InputType > |
| Determine the scaling factor of a ScaledKernel so that it has unit variance in feature space one on a given dataset. More... | |
| class | shark::OneClassSvmTrainer< InputType, CacheType > |
| Training of one-class SVMs. More... | |
| class | shark::PCA |
| Principal Component Analysis. More... | |