DCU Home | Our Courses | Loop | Registry | Library | Search DCU
<< Back to Module List

Latest Module Specifications

Current Academic Year 2025 - 2026

Module Title Advanced Machine Learning
Module Code CSC1106 (ITS: CA4015)
Faculty Computing School Engineering & Computing
NFQ level 8 Credit Rating 7.5
Description

This module will provide students with both a theoretical and practical grounding in modern machine learning. The module includes classical approaches for the purposes of historical context, conceptual development, interpretability and specific solution applicability. However, the primary emphasis is deep learning and contemporary approaches such as reinforcement learning. Both supervised and unsupervised contexts will be explored. Ethical considerations will be given significant emphasis throughout the course. The educational structure is based on a project-oriented approach with a mix of both group and individual activities. Students will gain hands-on experience using research-grade datasets, international challenges and practical tutorial sessions.

Learning Outcomes

1. Implement data pre-processing and feature engineering approaches appropriate to specific problem domains
2. Design a Machine Learning System suitable for a given problem with due consideration given to performance metrics, class/data skew and explainability requirements.
3. Design, train and evaluate a recommender system
4. Design, train and evaluate a machine learning solution for a custom research challenge introduced by instructor based on research being carried out at DCU at PhD level and beyond.
5. Explain machine learning concepts related to algorithm operation, bias/variance, fitting issues, types of ML.
6. Design, train and evaluate a machine learning solution for a sequential data challenge.
7. Describe the ethical issues surrounding artificial intelligence in the context of machine learning


WorkloadFull time hours per semester
TypeHoursDescription
Lecture24No Description
Laboratory12Taking place immediately after the lecture, the students put what they have learned in the lecture into immediate use, working in groups to tackle real machine learning challenge problems relevant to their current assignment
Assignment Completion80Completion of Assignments
Independent Study71.5Self-study of lecture material
Total Workload: 187.5
Section Breakdown
CRN20394Part of TermSemester 2
Coursework0%Examination Weight0%
Grade Scale40PASSPass Both ElementsY
Resit CategoryRC1Best MarkN
Module Co-ordinatorTomas WardModule Teacher
Assessment Breakdown
TypeDescription% of totalAssessment Date
AssignmentExecutable Paper Challenge25%Week 2
AssignmentCustom Challenge suggested by research carried out in the School of Computing25%Week 5
AssignmentRecommender Systems Challenge25%Week 8
In Class TestMCQ covering lecture material25%Week 12
Reassessment Requirement Type
Resit arrangements are explained by the following categories;
RC1: A resit is available for both* components of the module.
RC2: No resit is available for a 100% coursework module.
RC3: No resit is available for the coursework component where there is a coursework and summative examination element.

* ‘Both’ is used in the context of the module having a coursework/summative examination split; where the module is 100% coursework, there will also be a resit of the assessment

Pre-requisite None
Co-requisite None
Compatibles None
Incompatibles None

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Feature Engineering
The importance of features in machine learning including selection, synthesis, extraction. To include feature free approaches. Automatic feature development will be introduced here. Specific approaches for signal processing (time series), images and video and documents will be considered.

Similarity Based and Error Based Approaches
kNN, SVM, SVR, Kernel Methods

Deep Neural Networks
Backpropagation, convolutional neural networks, autoencoders, recurrent neural networks, deep neural network architectures, generative adversarial networks.

Cross Cutting Content
Automatic Machine Learning, Ensembling, Ethics, Interpretability, Explainability, Large Scale Machine Learning, Practical Implementation considerations, performance metrics, class and data skew.

Ensemble Methods
Bagging, boosting, stacking

Indicative Reading List

Books:
None

Articles:
None
Other Resources

  • 1: Book, Sutton & Barto, 2018, Reinforcement learning: An introduction, MIT Press,
  • 415497: 1, Book, Goodfellow, Bengio, Courville, 2016, Deep Learning,

<< Back to Module List View 2024/25 Module Record for CA4015