Mathematics for Machine Learning
"Think hard, not work hard." - Prof. R. C. T. Lee
Course time: 10:10–11:00, Tuesday and 14:10–15:00 Wednesday.
TA: Kuan-Hsun Tsou (鄒冠勲) (Room E814)
Location: E416 (Tuesday) and E509 (Wednesday) at Main Engineering Building, Tamkang University.
Textbooks and other reference material
- Mathematics for Machine Learning. Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong. Cambridge University Press. 2020. (link to the book)
- Elementary Linear Algebra - Applications Version. 12th Edition. Howard Anton, Chris Rorres, Anton Kaul. 2019.
Subjects we plan to cover
- Attendance (10%)
- Assignments + Quizzes (30%)
- Midterm (30%)
- Final Exam (30%)
*We thank Prof. Deisenroth for permitting us to use the textbook pdf and figures in our lecture slides.
- Course Introduction [slides]
- Linear Algebra - Basis, Rank, Linear Mappings & Affine Spaces [slides], [exercise 01]
- Linear Algebra - Norms, Inner Products & Orthogonality [slides]
- Linear Algebra - Projections & Gram-Schmidt Orthogonalization [slides]
- Linear Algebra - Eigenvalues, Eigenvectors, Eigenspaces, Cholesky Decomposition & Diagonalization [slides], [exercise 02]
- Linear Algebra - Singular Value Decomposition & Matrix Approximation [slides]
- Vector Calculus - Differentiation, Partial Differentiation & Gradients [slides], [exercise 03]
- Vector Calculus - Gradients of Vector-Valued Functions and Matrices [slides], [exercise 04]
- Vector Calculus - Backpropagation & Automatic Differentiation [slides]
- Vector Calculus - Linearization & Multivariate Taylor Series [slides]
- Probability and Distributions - Sum Rule, Product Rule, Bayes' Theorem & Summary Statistics [slides]
- Probability and Distributions - Gaussian Distribution & Change of Variables [slides], [exercise 05]
- Continuous Optimization - Gradient Descent and Constrained Optimization [slides]
- Continuous Optimization - Preliminary Convex Optimization [slides]
- Empirical Risk Minimization [slides]
- Maximum Likelihood Estimation & Maximum A Posteriori Estimation [slides]
- Probabilistic Modeling & Inference [slides]
- Linear Regression - Maximum Likelihood Estimation & Maximum A Posteriori Estimation [slides]
- Density Estimation with Gaussian Mixture Models [slides]
- Classification with Support Vector Machines [slides]
Any question is welcome.
Please contact Joseph, Chuang-Chieh Lin (Email to:
© 2004 Joseph Chuang-Chieh Lin