EE5434 - Machine Learning for Signal Processing Applications | ||||||||||
| ||||||||||
| * The offering term is subject to change without prior notice | ||||||||||
Course Aims | ||||||||||
The students will gain a fundamental understanding of basic and emerging machine learning models and their applications in processing signals in various fields such as smart health, bioinformatics, adaptive control theory, medical image analysis, etc. The course is designed so that the students can obtain the basic ideas and intuition behind modern machine learning methods as well as some formal understanding of how and why they work. Correspondingly, one set of topics will focus on the general theme of statistical inference, which will allow the students to apply the basic techniques to different types of data, such as sensor data, discrete samples from wearables, and medical images. Another set of topics will focus more on existing machine learning models/algorithms such as supervised learning (neural networks, support vector machines); unsupervised learning (clustering, dimensionality reduction); adaptive control; transfer learning. The students will also engage in discussions of recent applications of machine learning such as medical image analysis, multi-sensor data analysis, spatial and temporal signal processing. This course requires students to have prior knowledge on basic programming skills, at a level sufficient to write a reasonable computer program, basic probability theory and linear algebra. | ||||||||||
Assessment (Indicative only, please check the detailed course information) | ||||||||||
Continuous Assessment: 50% | ||||||||||
Examination: 50% | ||||||||||
To pass the course, students are required to achieve at least 30% in course work and 30% in the examination. # may include homework, tutorial exercise, project/mini-project, presentation | ||||||||||
Examination Duration: 2 hours | ||||||||||
Detailed Course Information | ||||||||||
| EE5434.pdf | ||||||||||
Useful Links | ||||||||||
| Department of Electrical Engineering | ||||||||||
