Study-Unit Description

Study-Unit Description


TITLE Applied Machine Learning

UM LEVEL 05 - Postgraduate Modular Diploma or Degree Course



DEPARTMENT Artificial Intelligence

DESCRIPTION This study-unit focuses on the applications of machine learning techniques to different context. The emphasis is on the following topics:

- Machine learning principle and types;
- Extracting statistical information and structure from data;
- Traditional Machine Learning Techniques and probabilistic modelling;
- Classification and clustering;
- Artificial Neural networks and Backpropagation;
- Deep neural networks;
- Reinforcement Learning;
- Evaluate the performance of Machine Learning Models;
- Practical optimization problems.

Study-unit Aims:

The aims of this study-unit are to:
- instil a deeper understanding and appreciation of advanced techniques employed to analyse data, build predictive models, and build computer systems that perform intelligent decisions;
- investigate the techniques involved in distinguishing different machine learning techniques that are best suited to deal with real world problems and datasets;
- pursue further investigation in how to extract data to build models, identify patterns, and visualise data.

Learning Outcomes:

1. Knowledge & Understanding
By the end of the study-unit the student will be able to:

- describe how to identify the correct machine learning techniques for an application;
- compare advanced machine learning concepts like artificial neural networks, deep neural networks, support vector machines, and decision trees among others;
- report on construct systems that learn from, and are driven by data.

2. Skills
By the end of the study-unit the student will be able to:

- prepare, examine, and model data;
- apply the methods learnt to real world examples and datasets;
- gain familiarity with tools and libraries used in machine learning applications.

Main Text/s and any supplementary readings:

- Stuart Russell and Peter Norvig. 2021. Artificial Intelligence: A Modern Approach (4th. ed.). Prentice Hall Press, USA.

STUDY-UNIT TYPE Lecture & Independent Online Learning

Assessment Component/s Assessment Due Sept. Asst Session Weighting
Project See note below Yes 100%
Note: Assessment due will vary according to the study-unit availability.

LECTURER/S Joel Azzopardi
Josef Bajada
Mark Bugeja
Ingrid Galea
Konstantinos Makantasis
Dylan Seychell (Co-ord.)


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 2023/4. It may be subject to change in subsequent years.