Artificial intelligence (deep learning) has achieved great success in many fields. For example, image recognition, medical image analysis, and self-driving cars. Each application has a specific neural network model and a learning strategy in the field of deep learning. This course will explore the deep learning architecture details and use computer vision-related applications as examples to introduce learning strategies. This course contains not only these essential expositions of deep Learning but also many practical programming tasks. The goal is to give students the ability to build a corresponding deep neural network based on their problems.

Artificial intelligence (deep learning) has achieved great success in many fields. For example, image recognition, medical image analysis, and self-driving cars. Each application has a specific neural network model and a learning strategy in the field of deep learning. This course will explore the deep learning architecture details and use computer vision-related applications as examples to introduce learning strategies. This course contains not only these essential expositions of deep Learning but also many practical programming tasks. The goal is to give students the ability to build a corresponding deep neural network based on their problems.

Artificial intelligence (deep learning) has achieved great success in many fields. For example, image recognition, medical image analysis, and self-driving cars. Each application has a specific neural network model and a learning strategy in the field of deep learning. This course will explore the deep learning architecture details and use computer vision-related applications as examples to introduce learning strategies. This course contains not only these essential expositions of deep Learning but also many practical programming tasks. The goal is to give students the ability to build a corresponding deep neural network based on their problems.

週次 Week | 進度說明 Progress Description |
---|---|

1 | Course Introduction |

2 | Machine learning: The data-driven approach |

3 | Loss Functions and Optimization |

4 | Introduction to Neural Networks / Multilayer Perceptron |

5 | Convolutional Neural Networks |

6 | Intro to Pytorch and Tensorflow under Ubuntu System |

7 | CNN Architectures: AlexNet, VGG / Final Project Proposal due |

8 | Training Neural Networks |

9 | In-class midterm |

10 | CNN Architectures: GoogLeNet, ResNet, DenseNet, EfficientNet, etc |

11 | Proposal presentation |

12 | Object Detection |

13 | Semantic Segmentation |

14 | Unsupervised Learning: Generative Models |

15 | Recurrent Neural Networks |

16 | Semi-Supervised learning |

17 | Invited talk |

18 | Final Project Presentation |

- 教師(teacher): 許志仲

111年8月26日以後本課程上課方式/After August, 26, 2022, this course will be conducted as follows: 全學期採線上教學/Online teaching throughout this semester

- 教師(teacher): 李政德

111年8月26日以後本課程上課方式/After August, 26, 2022, this course will be conducted as follows: 全學期採線上教學/Online teaching throughout this semester

課程大綱(Course Outline)

英授(Taught in English)

英授(Taught in English)

111年8月26日以後本課程上課方式/After August, 26, 2022, this course will be conducted as follows: 採數週線上、數週實體混成教學(15+3)/Some weeks online and some weeks in-person (Hybrid teaching 15+3)

- 教師(teacher): 林良靖

111年8月26日以後本課程上課方式/After August, 26, 2022, this course will be conducted as follows: 實體上課(依教務處公告處理)/In-person teaching(According to the Office of Academic Affairs announcement)

- 教師(teacher): 李俊毅

111年8月26日以後本課程上課方式/After August, 26, 2022, this course will be conducted as follows: 實體上課(依教務處公告處理)/In-person teaching(According to the Office of Academic Affairs announcement)