MIT503 Information Processing for Engineering Systems

Instructors: Dr Woon Wei Lee

This course provides a graduate level introduction to information processing techniques. Methods covered in this course fall into two main categories: in the first half of the course, students will be introduced to the use of Wavelets as a means of decomposing signals and datasets into scale and time based components. This allows interesting features and patterns to be isolated for further processing. Towards this end, one important class of pattern processing algorithms is Neural Networks, which will be covered in the second half of the course. Students will also have the opportunity to apply some of the techniques taught in class to real problems via the class project. This is typically a substantial problem and forms a major assessment component to the course. The balance of the assessment is in the form of coursework which includes written and computer based assignments.

Topics include: Sampling theory and representation of information; wavelets and time-frequency analysis; multi-scale data representations; feature identification and recognition; adaptive techniques; Feed-forward neural networks, supervised and unsupervised learning algorithms and methods for statistical learning.