| Pre-Requisites | DA221 |
| Co-Requisites | None |
| Instructional Hours | 40 |
| Instructional Mode | Lecture |
| Delivery Mode | In-Person / Blended / Online |
This course, Mathematics for Machine Learning (DS320), covers essential mathematical concepts for machine learning, including linear algebra, calculus, optimization, and probability theory. Mathematics forms the foundation of machine learning algorithms and techniques, and a solid understanding of these concepts is crucial for developing and understanding machine learning models.
By the end of this course, students will be able to:
The course content will be presented through a series of lectures, tutorials, and problem-solving sessions. Students will be evaluated through assignments, quizzes, and a final exam.
Throughout the semester, students will be given assignments that will require them to apply mathematical concepts to solve machine learning problems. These assignments will allow students to practice their mathematical skills in the context of machine learning.
At the end of the semester, students will take a final exam that will cover all the material presented in the lectures. The final exam will test students’ understanding and application of mathematical concepts in the context of machine learning. The exam will count towards a significant portion of the overall course grade.
The following is a general outline of the topics covered in the course:
| Week | Topic |
|---|---|
| 1 | Introduction to Linear Algebra for Machine Learning |
| 2 | Vectors and Matrices |
| 3 | Linear Transformations and Eigenvectors |
| 4 | Matrix Operations and Matrix Decompositions |
| 5 | Introduction to Calculus for Machine Learning |
| 6 | Derivatives and Gradients |
| 7 | Optimization for Machine Learning |
| 8 | Introduction to Probability Theory for Machine Learning |
| 9 | Probability Distributions and Expectation |
| 10 | Bayesian Probability and Conditional Probability |
| 11 | Statistical Inference |
| 12 | Final Exam Preparation and Course Reflection |