Download F21DL - School of Mathematical and Computer Sciences

Form C4
Version 4.0 (2010/2011)
Heriot-Watt University - Course Descriptor Template
1. Course
Code
F21DL
2. Course
Title
Data Mining and Machine Learning
5. School
Mathematical and Computer Sciences
7. Delivery:
Location &
Semester
Edin
SBC
Orkney
Dubai
IDL
Collaborative Partner
Approved Learning Partner
Sem 1
Sem…….
Sem………..
Sem……..
Sem….
Name…………………….....Sem..…...
Name …………………………………Sem………..
6. Course
Co-ordinator
8. Pre-requisites
F29AI AI and Intelligent Agents or basic knowledge of AI concepts and issues
9. Linked Courses
(specify if synoptic)
10. Excluded Courses
None
11. Replacement Courses
Code:
11
4. Credits
15
Dave Corne
None
12. Degrees for which
this is a core course
Date Of Replacement:
13. The course may be
delivered to:
3. SCQF
Level
UG only
PG only
MSc Artificial Intelligence, MSc Artificial Intelligence with
Speech and Multimodal Interaction, MSc Data Science
UG & PG
14. Available as an Elective?
Yes
No
15. Aims
To introduce students to the fundamental concepts and techniques used in data mining and machine learning.
To develop a critical awareness of the appropriateness of different data mining and machine learning techniques.
To provide familiarity with common applications of data mining and machine learning techniques.
16. Syllabus
Data Mining: Basic concepts (datasets, dealing with missing data, classification, statistics), regression analysis, cluster analysis (k-means clustering, hierarchical
clustering), unsupervised learning, self-organising maps, naïve Bayes, k-nearest-neighbour methods
Machine Learning: decision tree learning, ensemble methods (bagging and boosting, random forests), deep learning architectures, support vector machines
1/2
Form C4
Version 4.0 (2010/2011)
Heriot-Watt University - Course Descriptor Template
17. Learning Outcomes (HWU Core Skills: Employability and Professional Career Readiness)
Subject Mastery
Understanding, Knowledge and Cognitive
Skills
♦
♦
♦
Personal Abilities
Scholarship, Enquiry and Research (Research-Informed Learning)
Extensive understanding of the data mining process.
Detailed understanding of the mathematical basis of machine learning.
Critical awareness of the appropriateness and performance of different techniques.
Industrial, Commercial & Professional Practice
♦
♦
♦
♦
Autonomy, Accountability & Working with Others
Communication, Numeracy & ICT
Rational problem identification and definition.
Critical analysis and solution selection.
Thorough and robust preparation of testing strategies.
Reflection on system development and performance.
18. Assessment Methods
Method
19. Re-assessment Methods
Duration of Exam
Weighting (%)
Synoptic courses?
Method
(if applicable)
Coursework
Duration of Exam
Diet(s)
(if applicable)
100
Coursework
20. Date and Version
Date of Proposal
March 2014
Date of Approval by
School Committee
March 2014
Date of
Implementation
September 2014
Version
Number
2/2
1.0