課程名稱 |
(中文) 人工智慧程式設計與Python (英文) |
開課單位 | 資訊工程學系 | ||
課程代碼 | I3960 | ||||
授課教師 | 葉慶隆 | ||||
學分數 | 3.0 | 必/選修 | 選修 | 開課年級 | 大三 |
先修科目或先備能力:微積分、線性代數、機率統計、物件導向程式設計、資料庫系統 | |||||
課程概述與目標: 學習Python程式設計及用來建構類神經網路所需的基礎模組,包括NumPy、pandas、Matplotlib、PyTorch、Calculus、及Linear Algebra。類神經網路架構概念介紹,包括淺層、深層網路。tensorflow/kera工具操作應用練習。 以及人工智慧應用包括電腦視覺、及自然語言諸應用案例。此外也練習以python api管理語意網/連結資料(linked data)。 | |||||
教科書 | Python for Everybody: Exploring Data in Python 3 | ||||
參考教材 | AI Programming with Python, Udacity (MOOCS 課程) CS50's Introduction to Artificial Intelligence with Python, Harvard University Python Tutorial, w3schools.com NumPy Tutorial, w3schools.com Pandas Tutorial, w3schools.com Matplotlib Tutorial, w3schools.com Machine Learning, w3schools.com SymPy: a Python library for symbolic mathematics Learn pandas by Hernan Roja Python Deep Learning Tutorial, Tutorialspoint AI with Python – Neural Networks, Tutorialspoint |
課程大綱 | 學生學習目標 | 單元學習活動 | 學習成效評量 | 備註 | ||
週 | 單元主題 | 內容綱要 | ||||
1 | Python Programming (1) | 1. Background 2. Variables, expressions, and statements 3. Conditional execution 4. Anaconda, Jupyter Notebook, google colab |
1. Programming background 2. Variables, expressions, and statements 3. Conditional execution 4. Anaconda, Jupyter Notebook, google colab |
|
||
2 | Python Programming (2) | 1. Functions 2. Iteration 3. Strings |
1. Functions 2. Iteration 3. Strings |
|
||
3 | Python Programming (3) | 1. Files 2. Lists 3. Dictionaries |
1. Files 2. Lists 3. Dictionaries |
|
||
4 | Python Programming (4) | 1. Tuples 2. Regular Expressions |
1. Tuples 2. Regular Expressions |
|
||
5 | NumPy | 1. NumPy | 1. NumPy |
|
||
6 | NumPy, Pandas | 1. Numpy 2. Pandas |
1. Numpy 2. Pandas |
|
||
7 | Pandas, Matplotlib | 1. Pandas 2. Matplotlib |
1. Pandas 2. Matplotlib |
|
||
8 | Building A Logistic Regression in Python (1) | 1. Introduction to Logistic Regression 2. Problem Description and Datasets 3. Data exploration 4. Visualizations |
Building A Logistic Regression in Python 1. Introduction to Logistic Regression 2. Problem Description and Datasets 3. Data exploration 4. Visualizations |
|
||
9 | 期中考週 | 期中考試 | 期中考試 |
|
||
10 | Building A Logistic Regression in Python (2) | 5. Create dummy variables 6. Over-sampling using SMOTE 7. Recursive Feature Elimination 8. Implementing the model |
5. Create dummy variables 6. Over-sampling using SMOTE 7. Recursive Feature Elimination 8. Implementing the model |
|
教學要點概述: |