Latest Module Specifications
Current Academic Year 2025 - 2026
No Banner module data is available
| |||||||||||||||||||||||||||||||||||||||||
|
Description The principal purpose of the module is to provide students with knowledge in areas of mathematics that are required for Machine Learning. The knowledge is also required for many other engineering applications such as advanced circuit theory, quantum electronics and communication systems. | |||||||||||||||||||||||||||||||||||||||||
|
Learning Outcomes 1. Perform vector and matrix operations and apply to problems of data representation and transformation. 2. Apply the basic principles of probability theory, including the concepts of random variables, probability distributions, and conditional probability to model and analyze uncertainty in data. 3. Apply linear and non-linear regression techniques to model relationships between variables in data, evaluate model performance using appropriate metrics, and use these models to make predictions 4. Identify appropriate statistical analysis techniques and apply them to assess the quality of data models. 5. Compute gradients, partial derivatives, and directional derivatives and apply multivariate calculus to optimization problems. | |||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||
|
All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml |
|||||||||||||||||||||||||||||||||||||||||
|
Indicative Content and Learning Activities
Introduction What is machine learning? Mathematical underpinnings of machine learning. Review of Linear Algebra Vectors, matrices, inner and outer products, eigenvalues and eigenvectors, matrix inversion Probability Basic definition, probability density function, cumulative distribution function, common distributions, Normal distribution, Bayes’ Theorem, random variables, expectation, variance, moments, operations on random variables Statistics Parameter estimation, confidence intervals, hypothesis testing. Review of Multivariate Calculus Multivariate chain rule, Taylor series, gradients, partial derivatives. Regression Linear, non-linear and normal regression. Performance evaluation of regression models. Optimization What is optimization? Gradient descent as an optimization technique. | |||||||||||||||||||||||||||||||||||||||||
|
Indicative Reading List Books:
Articles: None | |||||||||||||||||||||||||||||||||||||||||
|
Other Resources None | |||||||||||||||||||||||||||||||||||||||||