Information in the Degree Programme Tables may still be subject to change in response to Covid-19

University Homepage
DRPS Homepage
DRPS Search
DRPS Contact
DRPS : Course Catalogue : School of Engineering : Postgrad (School of Engineering)

Postgraduate Course: Machine Learning in Signal Processing (MSc) (PGEE11175)

Course Outline
SchoolSchool of Engineering CollegeCollege of Science and Engineering
Credit level (Normal year taken)SCQF Level 11 (Postgraduate) AvailabilityAvailable to all students
SCQF Credits10 ECTS Credits5
SummaryMachine learning is a field devoted to creating algorithms that can learn to adapt from data examples (rather than human instruction). This course aims to introduce techniques for performing machine learning, pattern recognition, classification and adaption in the analysis of complex signals and data sets. The intended audience are those wanting the background required to apply machine learning methods but also those that may develop inclinations to develop new machine learning methods.

This is an advanced course. Students should not choose this class without the required background (see "Other Requirements" box); students without this background are strongly advised to discuss with their personal tutor or degree director their intention and then obtain approval from the course organiser. This course uses examples (from signal and image processing) to motivate theory and analyses the theoretical aspects and properties of different approaches. This course is not practical-based and will not be teaching a particular computational machine learning framework.

Introduction to Machine Learning, Pattern Recognition, Detection, Classification, Regression, Modelling, Statistical Inference, Cluster Analysis, Neural Networks, Convolutional Neural Networks, Generalisation theory and Cross-validation, Deep learning, Latent Variable Models, Component Analysis, Hidden Markov Models, Applications to Speech, Audio and Image Data.
Course description General concepts covered: Classification and recognition; Statistical inference and learning; Clustering; Feature selection and data reduction (e.g. PCA)
In addition, to develop further support background for the course, we will cover: optimisation in one or more dimensions (stochastic gradient descent and some of its variants); multivariate probability distributions; and necessary probability background.
We will also cover practical issues, sometimes via simple illustrative examples, or via demos and where appropriate computational examples. Through these we will learn about: implications of model design on the problem; considerations of cost/efficiency in approaching a machine learning problem; and common design pitfalls.
Entry Requirements (not applicable to Visiting Students)
Pre-requisites It is RECOMMENDED that students have passed Probability, Estimation Theory and Random Signals (PETARS) (MSc) (PGEE11164)
Prohibited Combinations Other requirements This course is open to Engineering students (MSc) and external students where this course is listed on the DPT. For external students where this course is not listed in your DPT, special permission from the course organiser is required.
This course builds on understanding of algebra, vectors and matrices, calculus, probability, and problem solving. For example, you will need to be able to differentiate linear algebra expressions with respect to vectors. Whilst some of the required details can be learned during the course, these take time to master. Hence a strong mathematical background is essential to fully appreciate the course and ensure a reasonable pace.
In addition, some prior appreciation of signal and image processing is assumed (for example, Fourier Transform, spatial and temporal correlation of data).
Information for Visiting Students
High Demand Course? Yes
Course Delivery Information
Academic year 2020/21, Available to all students (SV1) Quota:  110
Course Start Semester 2
Timetable Timetable
Learning and Teaching activities (Further Info) Total Hours: 100 ( Lecture Hours 22, Seminar/Tutorial Hours 11, Formative Assessment Hours 1, Summative Assessment Hours 2, Programme Level Learning and Teaching Hours 2, Directed Learning and Independent Learning Hours 62 )
Assessment (Further Info) Written Exam 100 %, Coursework 0 %, Practical Exam 0 %
Additional Information (Assessment) Written exam 100%
Feedback Not entered
Exam Information
Exam Diet Paper Name Hours & Minutes
Main Exam Diet S2 (April/May)2:00
Learning Outcomes
On completion of this course, the student will be able to:
  1. An understanding of pattern recognition and machine learning and will learn how to apply these methods to the processing of a broad class of signals;
  2. Recall a range of techniques and algorithms for pattern recognition and intelligent processing of signals and data, including neural networks and statistical methods;
  3. Derive and analyse properties of these methods;
  4. Discuss the relative merits of different techniques and approaches, implement some of these techniques in software (e.g. Matlab);
  5. Apply these methods to the analysis of signals and data.
Reading List
Essential reference: Duda, Hart and Stork, Pattern Classification
Additional material from: Theodoridis and Koutroumbas, Pattern Recognition and Watt, Borhani and Katsaggelos, Machine learning refined : foundations, algorithms, and applications

All are available via Leganto
Additional Information
Graduate Attributes and Skills Not entered
KeywordsPattern recognition,neuronal networks,hidden Markov models,machine learning,detection,classification
Course organiserProf Sotirios Tsaftaris
Tel: (0131 6)50 5796
Course secretaryMiss Jo Aitkenhead
Tel: (0131 6)50 5532
Help & Information
Search DPTs and Courses
Degree Programmes
Browse DPTs
Humanities and Social Science
Science and Engineering
Medicine and Veterinary Medicine
Other Information
Combined Course Timetable
Important Information