Module Code - Title:
CS4106
-
MACHINE LEARNING: METHODS AND APPLICATIONS
Year Last Offered:
2025/6
Hours Per Week:
Grading Type:
Prerequisite Modules:
CS4006
Rationale and Purpose of the Module:
The purpose of this module is to familiarise students with a targeted subset of the principles and methods involved in machine learning, focusing mainly on the field of evolutionary computation and associated paradigms.
Syllabus:
Following an overview of general machine learning methods and applications, the goal is to provide students with an understanding of the basic principles, methods and application domains for evolutionary computation.
Students will be introduced to a broad range of evolutionary computation techniques including genetic algorithms, genetic programming, and grammatical evolution. Different representational mechanisms including binary, Gray, real-valued and e-code will be discussed. Different approaches to the mutation and recombination operators will be presented. Fitness function types and interactive evolutionary computation will be introduced.
Depending on the particular expertise of the lecture involved in delivery of the module particular emphasis may be placed on application to areas such as neuroevolution, evolutionary robotics (including evolutionary humanoid robotics), automatic program synthesis, the parallelisation of sequential programs, and financial modelling and prediction. Potential societal, ethical and philosophical implications of advanced AI/ML technologies will be outlined.
Learning Outcomes:
Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)
On successful completion of this module, students will be able to:
1. Be aware of the main approaches taken in the machine learning field.
2. Describe the main paradigms involved in evolutionary computing, including genetic algorithms, genetic programming, grammatical evolution, and evolutionary strategies.
3. Explain and describe the principles involved in the training of artificial evolutionary systems.
4. Understand how to implement basic variants of some evolutionary algorithms.
5. Understand how evolutionary computation relates to other approaches to machine learning, including the relative advantages and disadvantages of the evolutionary computation approach.
Affective (Attitudes and Values)
N/A
Psychomotor (Physical Skills)
N/A
How the Module will be Taught and what will be the Learning Experiences of the Students:
Research Findings Incorporated in to the Syllabus (If Relevant):
Prime Texts:
A. E Eiben, & J. E. Smith (2015)
Introduction to Evolutionary Computing, 2nd ed.
, Springer Berlin Heidelberg.
D. Floreano, & C. Mattiussi (2008)
Bio-Inspired Artificial Intelligence: Theories, Methods, and Technologies
, MIT Press.
Other Relevant Texts:
T. Mitchell (1997)
Machine Learning
, McGraw-Hill
K. A. De Jong (2006)
Evolutionary computation: a unified approach
, MIT Press
S. Nolfi, and D. Floreano (2000)
Evolutionary robotics. The biology, intelligence, and technology of self-organizing machines
, MIT Press
R.S. Sutton, and A. G. Barto (1998)
Reinforcement learning: An introduction
, MIT press.
M. Eaton (2015)
Evolutionary Humanoid Robotics
, Springer Berlin Heidelberg.
Programme(s) in which this Module is Offered:
BSCOSYUFA - COMPUTER SYSTEMS
BSCGDEUFA - COMPUTER GAMES DEVELOPMENT
Semester(s) Module is Offered:
Spring
Module Leader:
Naa.Addo@ul.ie