本課程目標在培養學生學習機器學習技術的能力，使其能夠快速且有系統地掌握人工智慧技術的最新發展趨勢，並深入了解人工智慧的運作原理。
課程內容涵蓋完整的機器學習流程，從資料蒐集與前處理（Data Preprocessing）、資料視覺化（Data Visualization）及探索性資料分析（Exploratory Data Analysis, EDA）開始，學習如何整理、清理與理解資料特性。接著介紹機器學習的理論基礎，包括監督式學習、非監督式學習、分類與迴歸等重要概念，以及常見機器學習演算法與模型建構方法。
在深度學習部分，課程將深入探討人工神經網路（Neural Network, NN）與卷積神經網路（Convolutional Neural Network, CNN）的基本原理與架構設計，說明神經網路的學習機制、參數調整與模型訓練流程，並介紹 CNN 在影像辨識與電腦視覺領域中的實際應用。
課程將搭配實作範例與自主練習，引導學生運用真實資料進行分析、建立機器學習與深度學習模型、進行模型訓練與預測，並評估模型效能。透過理論與實務並重的教學方式，學生將具備從資料前處理、資料分析、機器學習模型建構，到神經網路與卷積神經網路應用的完整能力，為未來進階人工智慧課程及相關產業應用奠定扎實基礎。

The goal of this course is to cultivate students' ability to learn machine learning technology, so that they can quickly and systematically grasp the latest development trends of artificial intelligence technology, and have an in-depth understanding of the operating principles of artificial intelligence.
The course content covers the complete machine learning process, starting from data collection and preprocessing (Data Preprocessing), data visualization (Data Visualization) and exploratory data analysis (EDA), and learn how to organize, clean and understand the characteristics of data. Then the theoretical basis of machine learning is introduced, including important concepts such as supervised learning, unsupervised learning, classification and regression, as well as common machine learning algorithms and model construction methods.
In the deep learning part, the course will deeply explore the basic principles and architectural design of artificial neural networks (NN) and convolutional neural networks (CNN), explain the learning mechanism, parameter adjustment and model training process of neural networks, and introduce the practical application of CNN in the fields of image recognition and computer vision.
The course will be paired with practical examples and independent exercises to guide students to use real data to analyze, build machine learning and deep learning models, conduct model training and prediction, and evaluate model performance. Through a teaching method that pays equal attention to theory and practice, students will have complete capabilities from data pre-processing, data analysis, machine learning model construction, to neural network and convolutional neural network applications, laying a solid foundation for future advanced artificial intelligence courses and related industrial applications.

1.Deep Learning/ ISBN:0262035618/ MIT
2.Pattern Recognition and Machine Learning/ISBN:0387310738 /Springer

1.Deep Learning/ ISBN:0262035618/ MIT
2.Pattern Recognition and Machine Learning/ISBN:0387310738/Springer