Module Code - Title:
CS6501
-
MACHINE LEARNING AND APPLICATIONS
Year Last Offered:
2025/6
Hours Per Week:
Grading Type:
N
Prerequisite Modules:
Rationale and Purpose of the Module:
This module equips students with an understanding of the key principles and methods in the field of Machine Learning. Concepts will be illustrated using existing tool sets and case studies with a focus on the key steps needed such as data preparation and model validation. Students will learn to select, apply, analyse, and critique machine learning algorithms using real world noisy data.
This module will be offered on the MSc. Software Engineering, M.Eng Electronic and Computer Engineering, and the M.Sc. Business Analytics programmes.
Syllabus:
1. Fundamental concepts in Machine Learning such as train/test, supervised/unsupervised learning, generalisation and over fitting, and data pre-processing.
2. Linear, multiple, and polynomial regression.
3. An overview of Parametric vs. Non-Parametric classifiers.
4. Techniques for evaluating classifier performance including Confusion matrices, ROC curves, and AUC measures.
5. An overview of Cartesian paradigms in the field such as Inductive Decision Trees, Bayesian methods, and clustering.
6. Classification using techniques from the field of Computational Intelligence such as Evolutionary Algorithms (EAs) and Artificial Neural Networks (ANNs).
7. An introduction to Deep learning with a focus on Convolutional Neural Networks (CNNs) for classification.
8. Model selection and boosting.
9. Ethical issues in artificial intelligence and machine learning.
Learning Outcomes:
Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)
1. Describe the mechanics of a key Machine Learning algorithms with a focus on a critical appreciation of their benefits and liabilities.
2. Demonstrate a deep understanding of the importance of data pre-processing and analysis.
3. Select the appropriate machine learning algorithm for a particular data set that is in some sense optimal.
4. Apply machine learning algorithms to real world data sets.
5. Evaluate classifier performance using confusion matrices and ROC curves.
6. Reflect on the ethical challenges arising from the emergence of autonomous intelligent machines.
Affective (Attitudes and Values)
1. Appreciate the implications of bias in data for machine learning paradigms.
2. Defend the selection of machine learning paradigms.
3. Respond to ethical tensions where they arise as a result of the use of machine learning applications.
Psychomotor (Physical Skills)
Not applicable.
How the Module will be Taught and what will be the Learning Experiences of the Students:
The module will be taught through a combination of lectures and labs with support by guest speakers from industry partners with an international reputation for excellence in the development of smart applications. Students will learn to select, apply, analyse, and critique machine learning algorithms using real world noisy data in team-based lab settings. Research findings will be incorporated through the selection of key research papers published by CSIS/Lero faculty for discussion in lecture settings.
Research Findings Incorporated in to the Syllabus (If Relevant):
Prime Texts:
J. Watt, R. Borhanni, & A.K. Katsaggelos (2016)
Machine Learning Refined: Foundations, Algorithms and Applications
, Cambridge
H. Witten, E. Frank, M. Hall, & C. Pal (2016)
Data Mining: Practical machine learning tools and techniques
, Morgan Kaufmann
T. Mitchell (1997)
Machine Learning
, McGraw-Hill
A. E. Eiben and J. E. Smith (2015)
Introduction to Evolutionary Computation, Second Edition.
, Springer Berlin Heidelberg.
Other Relevant Texts:
S. Marsland (2014)
Machine Learning: An Algorithmic Perspective
, CRC Press
G. Luger (2009)
Artificial Intelligence (6th edition).
, Addison-Wesley
Programme(s) in which this Module is Offered:
MSSOENTFA - SOFTWARE ENGINEERING
Semester(s) Module is Offered:
Autumn
Module Leader:
Abdul.Razzaq@ul.ie