Module Catalogue 2021/22

NUS8306 : Data Analytics using Machine Learning

  • Offered for Year: 2021/22
  • Module Leader(s): Dr Zi Jie Choong
  • Lecturer: Dr Noori Kim
  • Owning School: NUIS
  • Teaching Location: Singapore
Semesters
Semester 2 Credit Value: 20
ECTS Credits: 10.0
Pre Requisites
Pre Requisite Comment

N/A

Co Requisites
Co Requisite Comment

N/A

Aims

Data science is an interdisciplinary field that uses Machine Learning methods, processes, algorithms, and systems to extract knowledge and insights from many structured and unstructured data. In the past decade, data analytics using machine learning has given us numerous ideas for optimisation in areas like manufacturing process, performance, quality assurance, and defect tracking, predictive and conditional maintenance, demand and throughput forecasting, automation control and energy sustainability.

Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. It involves the process of developing a model to find and learn the patterns embedded within a given big dataset and distinguish relevance from the irrelevant events. Such a process will require both statistical modelling and probabilistic reasoning approaches to be successful.

This module aims to provide a broad introduction to machine learning, data mining, and statistical pattern recognition technique to analyse information obtained from sensors such as images, sequential and categorical data

Outline Of Syllabus

1. Introduction to Machine Learning (ML): Concepts of Data Representation, Supervised
and Unsupervised Learning.
2. Basics: Naïve Bayesian Theorem, Linear prediction: Regression, Maximum Likelihood,
Regularisation.
3. Supervised Learning: Linear Classification, Logistic Regression (LR), Support Vector
Machines (SVM), Kernels, K-nearest Neighbours Classifier (KNN).
4. Neural Networks Representation and Backpropagation.
5. Optimisation Methods for ML System Design.
6. Unsupervised learning: Clustering.
7. Dimensionality Reduction (Feature Extraction): Principle Component Analysis (PCA),
Linear Discriminant Analysis (LDA).
8. Recommendation systems.
9. Data Science Ethics

Learning Outcomes

Intended Knowledge Outcomes

At the end of the module, students should:
•       Have knowledge of the fundamental issues and challenges of machine learning (ML) such
as data and model selection, model complexity, etc.
•       Have knowledge of the pros and cons of many popular ML approaches.
•       Recognise the underlying mathematical relationships and learning paradigms across
various ML algorithms.
•       Apply various ML algorithms to a range of real-world data-driven applications.
•       Employ a good ethical framework during data acquisition and analysis.

Intended Skill Outcomes

At the end of the module, students should be able to:
•       Prepare, manipulate, and visualise data using appropriate methods for machine learning.
•       Explain the working principles of accessible machine learning (ML) algorithms.
•       Develop and deploy programs with appropriate ML algorithms on given datasets for
data-driven analysis.
•       Recognise the ethical considerations regarding the privacy and control of data.

Teaching Methods

Teaching Activities
Category Activity Number Length Student Hours Comment
Scheduled Learning And Teaching ActivitiesLecture122:3030:00Lectures
Guided Independent StudyAssessment preparation and completion218:0036:00Coursework assignment preparation
Guided Independent StudyAssessment preparation and completion124:0024:00Revision for exam
Guided Independent StudyAssessment preparation and completion12:002:00Final exam
Scheduled Learning And Teaching ActivitiesSmall group teaching121:0012:00Tutorials
Guided Independent StudyIndependent study122:0024:00Lecture follow-up
Guided Independent StudyIndependent study121:0012:00Tutorial preparation
Guided Independent StudyIndependent study160:0060:00Review lecture notes, general reading, background reading, reading specified articles
Total200:00
Teaching Rationale And Relationship

The teaching is conducted via lectures and tutorial with small group discussions during class. This is complemented with self-study and preparation of tutorial solutions, coursework/project, and final examination to provide feedback on student learning. Teaching materials are made available to the students online for self-study and preparation in their own pace. Tutorial classes enable students to ask questions and clarify any doubts.

Due to the emerging Covid-19 situation, it is likely that some or all of the classes are conducted online. Attendance will be taken irrespective of whether the class is online or face-to-face, and students are expected to switch on their camera for online classes.

Reading Lists

Assessment Methods

The format of resits will be determined by the Board of Examiners

Exams
Description Length Semester When Set Percentage Comment
Written Examination1202A80Final exam
Other Assessment
Description Semester When Set Percentage Comment
Computer assessment2M20Quiz - Testing of pseudo programming for the deployment of data manipulation, processing, and basic analytical approach
Formative Assessments
Description Semester When Set Comment
Written exercise2MAssignment - designing a framework to recommend solutions to data-driven engineering problems - 1500 words per student
Assessment Rationale And Relationship

The written exam enables students to demonstrate their understanding and apply relevant knowledge and skills learnt to solve data analytical problems. The coursework assignment will provide students with hands-on opportunity to apply machine learning techniques on real-world data problem and generate meaningful analytical solutions to make sound data-driven decisions on practical issues

Timetable

Past Exam Papers

General Notes

N/A

Disclaimer: The information contained within the Module Catalogue relates to the 2021/22 academic year. In accordance with University Terms and Conditions, the University makes all reasonable efforts to deliver the modules as described. Modules may be amended on an annual basis to take account of changing staff expertise, developments in the discipline, the requirements of external bodies and partners, and student feedback. Module information for the 2022/23 entry will be published here in early-April 2022. Queries about information in the Module Catalogue should in the first instance be addressed to your School Office.