• |
Introduction |
1.5 hours |

• |
Version space learning; Computational learning theory |
4.0 hours |

• |
PAC-learning; VC-dimension; On-line learning; Winnow |
4.0 hours |

• |
Perceptrons; Neural Networks; Backpropagation |
6.0 hours |

• |
Genetic algorithms |
3.5 hours |

• |
Bayesian learning |
3.5 hours |

• |
Experimental design |
3.0 hours |

• |
Decision-tree learning |
3.5 hours |

• |
Covering algorithms for learning rule sets |
3.0 hours |

• |
Minimum description length |
3.5 hours |

• |
Clustering algorithms |
3.0 hours |

• |
Reinforcement learning |
3.5 hours |

• |
Markov decision processes |
3.0 hours |

Total |
45 hours |