The purpose of this module is to enable students to understand how data science and AI applies to real-world domains, including but not limited to health, business, marketing, transport and search domains
-
Domains overview (per domain): Overview of key processes, requirements and potential for data science/ AI (e.g. supply chain for business, diagnostics, wearables/EdgeAI for health); Decision and process support using data science and AI; characteristics and challenges of that domain with regard to Data Science and AI.
-
Case studies of successful and not successful implementations of AI in domains under study.
-
Future directions per domain wrt data science and AI, awareness of AI state of the art take up and potential per domain, and understanding the pathway and challenges to that future, including technical, people-based, ethical and legal factors.
-
Domain Data: Types of data used in each domain, sample dataset exploration, understanding of data limitations, privacy requirements, availability and practical usages.
-
Knowledge, ML Models and evaluation: Machine learning approaches that are characteristic of each domain, domain specific metrics, available knowledge models (e.g. SNOMED and LOINC for health).
-
Critical analysis of data science and AI approaches/ systems within application domains.
-
Artificial Intelligence use per domain: Including but not limited to Data-driven AI, Generative AI, Natural Language Processing, Robotics, Virtual Reality, Knowledge Driven AI/Expert Systems.
-
Researching the latest development in applications domains: Research sources, appropriate public-facing and peer reviewed publications.
-
Implementation of an ML pipeline for a domain task
This module will include the use of case studies to support and reinforce the concepts on the syllabus.
In class teaching hours will be supplied by practical lab work where concepts can be explored in exercises, and case studies. Students will be encouraged to discover and research relevant real-world cases of the domain concepts being taught and to investigate domain specific knowledge based around the weekly tutorial sessions. .
The module will also include the examination of datasets per domain, where appropriate, and the use of the data for an illustrative Machine learning pipeline.
| Module Content & Assessment | |
|---|---|
| Assessment Breakdown | % |
| Formal Examination | 70 |
| Other Assessment(s) | 30 |