DCU Home | Our Courses | Loop | Registry | Library | Search DCU

Module Specifications..

Current Academic Year 2023 - 2024

Please note that this information is subject to change.

Module Title Machine Learning in Context
Module Code CA3110
School School of Computing
Module Co-ordinatorSemester 1: Claudia Mazo
Semester 2: Claudia Mazo
Autumn: Claudia Mazo
Module TeachersStephen Power
NFQ level 8 Credit Rating 7.5
Pre-requisite None
Co-requisite None
Compatibles None
Incompatibles None
Coursework Only

The purpose of this module is to provide an overview of the tools, techniques and purpose of machine learning. Students will participate in a variety of innovative teaching activities to distinguish approaches and supervised and unsupervised methodologies within machine learning. In addition, they will evaluate the effects and implications of Machine Learning(ML) on sustainability and society and the role of explainable-AI on ML adoption. The module is underpinned by Challenge Based Learning (CBL) which is an emerging pedagogy that involves students working in teams with stakeholders to investigate and co-create solutions for significant societal problems will follow a three phase approach (Engage - Investigate - Act). Through a process of collaborative engagement with peers, academics, and stakeholders, students will develop solutions to real-world challenges. Students will also investigate the application of machine-learning techniques to specific problems in the discipline of Physics, such as exoplanet detection, materials discovery or feature detection in microscopy.

Learning Outcomes

1. Explain the key concepts and applications of Machine Learning(ML).
2. Explain how neural networks can be trained to learn physical concepts.
3. Distinguish between supervised and unsupervised Machine Learning(ML) methods (when and how to apply them).
4. Apply the appropriate machine learning technique to a given challenge.
5. Apply the Cross Industry Standard Process for Data Mining - Crisp-dm framework ML lifecycle Overarching process - iterative process.
6. Prepare a case study on a machine-learning solution to a specific research problem in physics.
7. Develop a predictive machine-learning model using a physics-relevant data set.
8. Evaluate a given machine learning solution from different perspectives (performance metrics, human evaluation, ethics ) in a general and domain specific context (physics-relevant data set).

Workload Full-time hours per semester
Type Hours Description
Lecture18Module lectures
Class Presentation9Students will present on topics in ML to other students
Online activity36Access to digital resources
Group work36Students will work on various aspects of the module in groups
Assignment Completion36Students will work on various assignments throughout the module
Independent Study40.5Students will study the module material, related resources and references
Total Workload: 187.5

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

Applications of Machine Learning in Physics
Case studies highlighting the application of Machine Learning(ML) techniques to make predictions in different areas of physics, including astrophysics, materials, microscopy and statistical mechanics.

Hands-on Prediction of Physical Properties
How to prepare physical data sets and choose appropriate ML methods to make predictions.

Learning Physical Concepts
How neural networks represent data and how autoencoder networks can “learn” physical models.

Assessment Breakdown
Continuous Assessment100% Examination Weight0%
Course Work Breakdown
TypeDescription% of totalAssessment Date
AssignmentThis assignment will enable students to demonstrate an understanding of machine learning and its application to physical problems35%As required
Digital ProjectThis assessment will involve the development of an artefact which demonstrates an students understanding of method selection and experimental design.20%Once per semester
Group presentationThese assessments require students to present (a) on the societal benefits of machine learning with an emphasis on the ethical implications of machine learning and (b) on the application of machine learning to a specific problem in modern physics research.25%As required
Oral ExaminationThis will be an interactive oral exam where students discuss their artifact on method selection and experimental design.20%Once per semester
Reassessment Requirement Type
Resit arrangements are explained by the following categories;
1 = A resit is available for all components of the module
2 = No resit is available for 100% continuous assessment module
3 = No resit is available for the continuous assessment component
This module is category 1
Indicative Reading List

    Other Resources

    Programme or List of Programmes
    PANBSc Physics with Data Analytics

    My DCU | Loop | Disclaimer | Privacy Statement