Type of Credit: Partially Required
Credit(s)
Number of Students
本課程介紹人工智慧的基礎知識，包含智慧型代理人、搜尋問題與技術、知識推理、機率推理、機器學習的技術與應用等。課程中除了介紹基本理論，也會適時加入程式範例與程式作業（以 Python 為主），因此，希望選修同學具備 Python 的撰寫和執行能力。
能力項目說明
本課程為資訊科學系同學們介紹人工智慧的技術發展與基礎知識，如搜尋問題、知識推理、機率推理、機器學習的技術與應用等，以銜接進階的人工智慧課程，如深度學習、自然語言處理、電腦視覺等。
| 教學週次Course Week | 彈性補充教學週次Flexible Supplemental Instruction Week | 彈性補充教學類別Flexible Supplemental Instruction Type |
|---|---|---|
|
週次 Week |
課程主題 Topic |
課程內容與指定閱讀 Content and Reading Assignment |
教學活動與作業 Teaching Activities and Homework |
學習投入時間 Student workload expectation |
|
|
課堂講授 In-class Hours |
課程前後 Outside-of-class Hours |
||||
|
1 |
Introduction & Search Problems |
AIMA Ch. 1-2 |
預習與閱讀、課堂公告 |
2 |
2 |
|
2 |
Uninformed Search |
AIMA Ch. 3 |
預習與閱讀、課堂公告 |
3 |
2 |
|
3 |
Informed Search |
AIMA Ch. 3 |
預習與閱讀、課堂公告 |
3 |
2 |
|
4 |
Local Search Adversarial Search |
AIMA Ch. 4, 6 |
預習與閱讀、課堂公告 |
3 |
2 |
|
5 |
Constrained Search Problems |
AIMA Ch. 5 |
預習與閱讀、課堂公告 |
3 |
2 |
|
6 |
Knowledge & Reasoning |
AIMA Ch. 7-9 |
預習與閱讀、課堂公告 |
3 |
2 |
|
7 |
Uncertain Knowledge |
AIMA Ch. 13, 14 |
預習與閱讀、課堂公告 |
3 |
2 |
|
8 |
Probabilistic Reasoning |
AIMA Ch. 14, 15 |
預習與閱讀、課堂公告 |
3 |
2 |
|
9 |
期中考 |
- |
- |
- |
- |
|
10 |
ML-basics |
AIMA Ch. 19 |
預習與閱讀、課堂公告 |
3 |
2 |
|
11 |
Supervised Learning |
AIMA Ch.19, DM-W Ch.4 |
預習與閱讀、課堂公告 |
3 |
2 |
|
12 |
Unsupervised Learning |
DM-H Ch. 8 |
預習與閱讀、課堂公告 |
3 |
2 |
|
13 |
Deep Learning |
AIMA Ch. 22 |
預習與閱讀、課堂公告 |
3 |
2 |
|
14 |
校慶活動停課 |
- |
- |
- |
- |
|
15 |
Natural Language Processing |
AIMA Ch. 24, 25 |
預習與閱讀、課堂公告 |
3 |
2 |
|
16 |
Generative AI |
Ch. 1 [5] |
預習與閱讀、課堂公告 |
3 |
2 |
|
17 |
期末論文報告 |
- |
期末論文報告 |
- |
- |
|
18 |
自主學習 |
- |
線上學習資源 |
- |
- |
作業 60%(手寫作業+程式作業)；期中考試 30%；期末論文報告 10%
1. [AIMA] Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, Fourth Edition, Pearson FT Press, 2020
2. [DM-W] Ian H. Witten, Eibe Frank, Mark A. Hall, and Christopher J. Pal, Data Mining: Practical Machine Learning Tools and Techniques, Fourth Edition, Morgan Kaufmann, 2017
3. [DM-H] Jiawei Han, Jian Pei, and Hanghang Tong, Data Mining: Concepts and Techniques, Fourth Edition, Morgan Kaufmann, 2022
4. Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, Third Edition, O'Reilly Media, 2022.
5. David Foster, Generative Deep Learning, O'Reilly Media, 2023.