教學大綱與進度

課程基本資料：

學年期	課號	課程名稱	階段	學分	時數	修	教師	班級	人	撤	備註
111-2	316361	機器學習基礎	1	3.0	3	★	劉俊麟	電機四丁	10	1	2/7改禮拜三第89A節

教學大綱與進度：

教師姓名	劉俊麟　教師諮商時間(Office Hours)
Email	junlin@mail.ntut.edu.tw
最後更新時間	2023-02-12 15:24:51
課程大綱	理解機器學習(Machine Learning)的原理與應用是相對重要的，掌握機器學習相關之數學基礎將有助於理解機器學習使用方法之假設和局限性，輔以對機器學習較具經典代表性應用案例的深入探討，將有助於在面對新的問題時，能有效與快速地提出以機器學習為基礎的新興解決方案。課程將以兩部份來進行，第一部份介紹機器學習相關的數學基礎理論包含線性代數、幾何解析、矩陣分解、機率與最佳化等；第二部份則以第一部份之理論為基礎，探討機器學習相關的衍生應用如線性回歸、維度降低、密度估計和分類等應用。 While machine learning software is available to design and train rich and flexible machine learning systems, the mathematical foundations of machine learning are important in order to understand fundamental principles for creating new machine learning solutions, and learn about the inherent assumptions and limitations of the methodologies. This course will contain two parts, where Part I lays the mathematical foundations in Linear Algebra, Analytic Geometry, Matrix Decomposition, and Probability theory and Optimization. Part II applies the concepts from Part I to a set of fundamental machine learning problems including Regression, Dimensionality Reduction, Density Estimation, and Classification.
課程進度	*** Linear Algebra *** Week1-2: Course overview and Chapter 2 Linear Algebra, Linear Equation, Matrics, Vector Space Week3-4: Chapter 3 Analytic Geometry, Inner Product, length & Angle, Orthonormal Basis, Orthogonal Projection Week5-6: Chapter 4 Matrix Decomposition, Determine, Eigenvalues, Eigenvectors, Eigendecomposition and Diagonalization Week7-8: Least Square Solution and Chapter 10 Dimension Reduction with PCA (Principal Component Analysis) Week9: Midterm Exam. *** Probability *** Week10-11: Chapter 5 Vector Calculus, Partial Differentiation and Gradients Week12-13: Chapter 6 Probability & Distributions, Probability Space, Discrete and Continuous Probability Week14-15: Chapter 9 Linear Regression, Parameter Estimation, Bayesian Linear Regression *** Optimization *** Week16-17: Chapter 7 Continuous Optimization, Gradient Descent, Convex Optimization Week18 Final Exam.
評量方式與標準	出席: 10% 課堂參與度: 5% 作業: 25% 期中考: 30% 期末考：30%
使用教材、參考書目或其他	【遵守智慧財產權觀念，請使用正版教科書，不得使用非法影印教科書】 使用外文原文書：是 Textbook: Mathematics for Machine Learning by Marc Peter Deisenroth, et al., 2020, Cambridge University Press (東華書局代理)
課程諮詢管道	可透過email (junlin@ntut.edu.tw)聯繫教師，就課程內容進行email或線上會議諮商，或可於教師規劃的學期諮商時段以email預約以進行面對面諮商與討論
備註	因應疫情發展，本學期教學及授課方式請依照學校網頁所公布之訊息為準： (https://oaa.ntut.edu.tw/p/404-1008-98622.php?Lang=zh-tw) 疫情嚴重期間將依學校公告改採線上教學，以線上會議軟體如MS Teams或Google Meet進行線上教學與討論