Use lasvm to train a given problem.

1 2 3 4 | ```
lasvmTrainWrapper(x, y, gamma, cost, degree = 3, coef0 = 0L,
optimizer = 1L, kernel = 2L, selection = 0L, termination = 0L,
sample = 0, cachesize = 256L, bias = 1L, epochs = 1L,
epsilon = 0.001, verbose = FALSE)
``` |

`x` |
data matrix |

`y` |
training labels |

`gamma` |
RBF kernel bandwidth |

`cost` |
regularization constant |

`degree` |
degree for poly kernel |

`coef0` |
coefficient for poly kernel |

`optimizer` |
type of optimizer |

`kernel` |
kernel type |

`selection` |
selection strategy |

`termination` |
criterion for stopping |

`sample` |
parameter for stopping criterion, e.g. seconds |

`cachesize` |
size of kernel cache |

`bias` |
use bias? |

`epochs` |
number of epochs |

`epsilon` |
stopping criterion parameter |

`verbose` |
verbose output? |

a list consisting of SV matrix of support vectors alpha vector of alpha coefficients bias bias term

Questions? Problems? Suggestions? Tweet to @rdrrHQ or email at ian@mutexlabs.com.

All documentation is copyright its authors; we didn't write any of that.