本課程旨在介紹深度學習之理論基礎，課程內容涵蓋類神經網路、卷積神經網路、模型訓練與測試流程、損失函數、優化器、學習曲線分析、模型評估指標與基礎結果判讀等主題。透過講授、示範與簡易實作練習，培養學生運用數學、科學與電機工程知識思考深度學習模型之能力，並建立使用程式語言進行基礎模型訓練、分析與應用的能力。

This course aims to introduce the theoretical basis of deep learning. The course content covers topics such as neural networks, convolutional neural networks, model training and testing processes, loss functions, optimizers, learning curve analysis, model evaluation indicators and basic result interpretation. Through lectures, demonstrations and simple practical exercises, students will develop their ability to use mathematics, science and electrical engineering knowledge to think about deep learning models, and build their ability to use programming languages ​​for basic model training, analysis and application.

1.Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016.
2.斎藤康毅，《Deep Learning：用 Python 進行深度學習的基礎理論實作》，吳嘉芳譯，歐萊禮，2017。
3.王琦、楊毅遠、江季，《深度學習詳解｜台大李宏毅老師機器學習課程精粹》，碁峰，2025。

1.Ian Goodfellow, Yoshua Bengio, and Aaron Courville, Deep Learning, MIT Press, 2016.
2. Saito Yasuki, "Deep Learning: Basic Theoretical Implementation of Deep Learning with Python", translated by Wu Jiafang, O'Reilly, 2017.
3. Wang Qi, Yang Yiyuan, and Jiang Ji, "Detailed Explanation of Deep Learning | Essence of Machine Learning Course by Teacher Li Hongyi of National Taiwan University", Qi Feng, 2025.