Skip to navigation | Skip to main content | Skip to footer

COMP61021 Representation Learning syllabus 2020-2021

COMP61021 materials

COMP61021 Representation Learning

Level 6
Credits: 15
Enrolled students: pending

Course leader: Ke Chen

Additional staff: view all staff


  • Pre-Requisite (Compulsory): COMP61011

Assessment methods

  • 100% Coursework
Sem 1 & 2 w11-12,15-17 ONLINE DROP-IN Wed 09:00 - 10:00 -
Sem 1 & 2 w11-12,15-17 ONLINE LabORATORY Wed 10:00 - 13:00 -
Sem 1 & 2 w11-12,15-17 INDEPENDENT STUDY Wed 13:00 - 18:00 -
Themes to which this unit belongs
  • Learning from Data


This course unit detail provides the framework for delivery in 20/21 and may be subject to change due to any additional Covid-19 impact. Current students should see Blackboard/course unit related emails for any further updates.

A major component of machine learning and AI is dealing with extracting the useful information underlying data, in particular, for high dimensional data. The recent success of deep learning is also attributed to effective data representation. As an emerging area in machine learning, representation learning can extract features from raw data, discover explanatory factors of variation behind data and tackle tough issues arising from high dimensional data. Representation learning has been successfully applied to many domains such as computer vision, audio/speech information processing, natural language processing/understanding, robotics and a variety of medical applications.

In this course, we will consider how to develop core algorithms for representation learning and gain insights into these algorithms from theoretical and empirical perspectives. We will demonstrate how essential algorithms are developed in a systematic way as well as how important algorithms can be applied through the use of examples and real world problems. We will cover related key approaches from machine learning, statistics and deep neural networks in this advanced machine learning course unit.


This course unit aims to introduce students to classical and state-of-the-art approaches to representation learning and provides experience of research such as literature review and self-learning from research papers. In particular, transferable knowledge/skills essential to original researches are highlighted in this course unit.


  • Introduction, background and mathematics essential
  • Linear model: principal component analysis and canonical correlation analysis
  • Manifold learning: background, MDS, ISOMAP and LLE algorithms
  • Autoencoder: neural network essential, shallow autoencoder, deep autoencoder and generative modelling via autoencoder
  • Clustering analysis: overview, partitioning, spectral, hierarchical and ensemble clustering algorithms

Teaching methods


three hours per week (5 weeks)


three hours per week (5 weeks)

Feedback methods

In general, feedback is available for the assessed work.

For coursework, the feedback to individuals will be offered.

For exam, the general feedback to the whole class will be given in writing.

Study hours

  • Lectures (15 hours)
  • Practical classes & workshops (15 hours)

Employability skills

  • Analytical skills
  • Innovation/creativity
  • Project management
  • Oral communication
  • Problem solving
  • Research
  • Written communication

Learning outcomes

On successful completion of this unit, a student will be able to:

On successful completion of this unit, a student will be able to:

  • understand the general motivation and main ideas underlying representation learning
  • describe the curse of dimensionality and its implication in different learning paradigms
  • understand the advantages and the disadvantages of the learning algorithms studied in the course unit and decide which is appropriate for a particular application
  • derive the linear representation learning algorithms from scratch
  • apply the learning algorithms studied in the course unit to simple data sets for feature extraction related applications and visualisation of high-dimensional data
  • implement the core learning algorithms studied in the course unit as well as apply those to real-world datasets
  • evaluate the performance of the core learning algorithms studied in the course unit and whether such a learning algorithm is appropriate for a particular problem
  • understand and appreciate main ideas underlying state-of-the-art representation learning algorithms
  • make a connection between representation learning and other relevant areas in machine learning

Reading list

Introduction to machine learning Alpaydin, Ethem.0262028182; 9780262028189; 0262325748 (electronic bk.); 9780262325745 (electronic bk.)The MIT Press[2014]
Deep learning Goodfellow, Ian,0262035618 (hardcover : alk. paper); 9780262035613 (hardcover : alk. paper)MIT Press[2016]
Bayesian reasoning and machine learning Barber, David,0521518148 (hbk.) :; 9780521518147 (hbk.) :Cambridge University Press2012.
Mathematics for Machine LearningDeisenroth, Marc Peter ; Faisal, A. Aldo ; Ong, Cheng Soon9781108455145null2020-02-29

Additional notes

Course unit materials

Links to course unit teaching materials can be found on the Department of Computer Science website for current students.