本課程為人工智慧的相關課程，首先介紹機器學習的基礎概念，如:監督式學習、與非監督學習的相關技術，並透過實例介紹機器學習基礎的model與核心概念與應用。當學生具備有基本機器學習基礎後，再介紹類神經網路及深度學習，包含如何訓練及優化類神經網路(NN)、深度神經網路(DNN)與卷積神經網路(CNN)…等深度學習模型，最後介紹強化式學習。透過TensorFlow /Keras所提供的模組與實務專案讓同學動手實作。This course is a course related to artificial intelligence. It first introduces the basic concepts of machine learning, such as supervised learning, and related technologies of unsupervised learning. It also introduces basic models and core concepts and applications of machine learning through examples. After students have basic machine learning foundation, they will introduce neural networks and deep learning, including how to train and optimize neural networks (NN), deep neural networks (DNN) and convolutional neural networks (CNN)... Wait for the deep learning model, and finally introduce reinforcement learning. Let students practice through the modules and practical projects provided by TensorFlow/Keras.
1.斎藤康毅，Deep Learning-用Python進行深度學習的基礎理論實作，第一版，碁峰出版社.
2.斎藤康毅，Deep Learning 2-用Python進行自然語言處理的基礎理論實作，第一版，碁峰出版社.
3.賴屹民，精通機器學習-使用Scikit-Learn, Keras與TensorFlow，第二版，碁峰出版社.
1. Yasuki Saito, Deep Learning-Basic theoretical implementation of deep learning with Python, first edition, Qifeng Publishing House.
2. Yasuki Saito, Deep Learning 2-Basic theoretical implementation of natural language processing with Python, first edition, Qifeng Publishing House.
3. Lai Yimin, Mastering Machine Learning - Using Scikit-Learn, Keras and TensorFlow, Second Edition, Qifeng Publishing House.
| 評分項目 Grading Method | 配分比例 Grading percentage | 說明 Description |
|---|---|---|
| 期中考期中考 midterm exam |
20 | |
| 期末展示期末展示 Final presentation |
25 | |
| 上課作業上課作業 Classwork |
45 | |
| 出席狀況與其他出席狀況與其他 Attendance and other |
10 |
