Machine Learning (Elective)

Back To Course

Next Module

Parent Programme

Bachelor in Computing (Level 7 NFQ)

NFQ Level 7 & Reference

Level 7 / Ref: M3.11

Duration

12 Weeks X 3 Hours per week

MODULE TITLE

Machine Learning (Elective)

STAGE

Award

Module Credit Units

ECTS: 5

Machine Learning (Elective)

Introduction to Machine Learning

The aims of this module are to provide learners with an understanding of key concepts, techniques, and practical skills in the field of machine learning. With this grounding learners will be trained to push further and communicate results to a variety of audiences (technical, adept, expert). A focus on the interpretability, repeatability and reproducibility of work to instil trust in results presented will be at the forefront. Key issues in ethics will also be covered as these societal challenges provide varying levels of social acceptability in application areas.

Indicative Syllabus Content

Theoretical base for machine learning

Probability and statistics
Linear mathematics
Supervised learning vs unsupervised learning

Considerations for data in machine learning

Data types and structures
Pre-processing and cleaning
Feature extraction and engineering
Data augmentation
Data imputation

Unsupervised learning

K-means clustering
Agglomerative clustering
Density-Based Spatial Clustering of Applications with Noise
Dimensionality reduction (PCA and UMAPS)

Model fitting

Cross validation
Over fitting and under fitting
Precision and accuracy
F1 score

Supervised learning

Linear regression
Logistic regression
Decision trees and random forests
K-nearest neighbours
Support vector machines

Ethics

Case studies and report writing
Transparency and interpretability of results
Practical limitations due to ethical concerns

Minimum Intended Learning Outcomes (MIMLOs)

Upon successful completion of this module, the learner should be able to:

MIMLO1

Discuss the theory behind machine learning applications and be capable of articulating constructive arguments for or against any particular technique for a given dataset or use case.

MIMLO2

Build a machine learning model using common industry tools.

MIMLO3

Make arguments behind data augmentation or data imputation as needed for unideal datasets.

MIMLO4

Demonstrate consciousness of ethical issues and cite case studies for consequences in a cost/benefit analysis.

MIMLO5

Evaluate learning methods and compare using standard metrics and select a model as appropriate for a given task

Assessment

MIMLOs

Assessment

Percentage

1, 2, 3, 4, 5

CA 1 - CA 6: Coding Assignments

Total 100%

Proctored Written Exam

All Assessments

Reassessment Opportunity

Where the combined marks of the assessment and examination do not reach the pass mark the learner will be required to repeat the element of assessment that they failed. Reassessment materials will be published on Moodle after the Examination Board and will be aligned to the MIMLOs and learners will be capped at 40% unless there are personal mitigating circumstances.

Aims & Objectives

The Machine Learning module will ensure learners meet the following objectives:

Basic knowledge of machine learning concepts
Familiarity with unsupervised learning methods
Familiarity with supervised learning methods
Practical skill with industry tools (python scikit learn)
Grounding in ethics specific to machine learning issues
Communication skills to deliver reports to a range of audiences

[TheChamp-Sharing]

Apply Now