| CODE | CCE2502 | ||||||||||||||||
| TITLE | Pattern Recognition and Machine Learning | ||||||||||||||||
| UM LEVEL | 02 - Years 2, 3 in Modular Undergraduate Course | ||||||||||||||||
| MQF LEVEL | 5 | ||||||||||||||||
| ECTS CREDITS | 5 | ||||||||||||||||
| DEPARTMENT | Communications and Computer Engineering | ||||||||||||||||
| DESCRIPTION | Five fundamental paradigms in pattern recognition and machine learning are studied in this study-unit 鈥� Similarity based models, 福利在线免费-based models, error-based models, probability based models and clustering models. A theoretical and applied approach is adopted and practical examples that reinforce the techniques studied are cited and discussed. This study-unit is delivered from a computing point of view and it is therefore expected that the student is conversant in a high level programming language. This unit is a useful companion/complementary unit to other units or areas that benefit from data-driven models and provides the foundation for further studies in the area. Study-unit Aims: This unit aims to: - Teach the data-driven modelling methodology and compare to physics-driven models; - Assist students with studying the fundamental and basic pattern recognition methods, mainly linear regression, logistic regression, decision trees, distance based methods and probabilistic methods; - Assist students with studying the basic learning methods, i.e derivative based methods, distance metrics, information theory based methods and joint distribution methods. Learning Outcomes: 1. Knowledge & Understanding By the end of the study-unit the student will be able to: - Differentiate between physics-driven models and data-driven models; - Recognise the various fields in organised and labeled data; - Differentiate between a predictive and a generative model; - Recognize patterns in data and select a model that fits the pattern; - Recognize the various distance measures and locate examples in n-dimensional vector space; - Apply a distance measure to discover neighbouring examples; - Apply Entropy and information gain to select the inputs that are most informative of the model output; - Differentiate between linear regression and logistic regression models; - Differentiate between the analytical and numerical solutions to a regression model; - Recognise the local and global optimisation problem; - Describe the gradient based optimisation method; - Formulate a probabilistic model for a simple classification problem; - Formulate a probabilistic Markov model for times series modelling; - Use a measure of accuracy for the output results. 2. Skills By the end of the study-unit the student will be able to: - Elaborate on the problem definition and abstract a conceptual model; - Select a pattern recognition algorithm to implement the conceptual model; - Implement the selected algorithm or model in a high level language; - Optimize, Tune and validate a model using a principled technique; - Evaluate the model output; - Program in Python or equivalent. Main Text/s and any supplementary readings: Main Text - J.D. Kelleher, B. Mac Namee and A. D鈥橝rcy, 鈥淔undamentals of Machine Learning for Predictive Data Analytics鈥�, MIT Press. (main library 鈥� Q325.5 .K455) |
||||||||||||||||
| ADDITIONAL NOTES | Pre-Requisite qualifications: Computer Programming in a high-level language and Mathematics in calculus, linear algebra, statistics and probability. | ||||||||||||||||
| STUDY-UNIT TYPE | Lecture, Independent Study, Practicum & Tutorial | ||||||||||||||||
| METHOD OF ASSESSMENT |
|
||||||||||||||||
| LECTURER/S | Adrian F. Muscat |
||||||||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2025/6. It may be subject to change in subsequent years. |
|||||||||||||||||