Skip to main content

Module

EEE3022 : Introduction to Machine Learning

  • Offered for Year: 2022/23
  • Module Leader(s): Dr Kabita Adhikari
  • Owning School: Engineering
  • Teaching Location: Newcastle City Campus
Semesters
Semester 2 Credit Value: 10
ECTS Credits: 5.0

Aims

Machine Learning is a branch of Artificial Intelligence which focuses on design of intelligent algorithms that enable a computer to learn concepts and make decisions without being explicitly programmed. These algorithms are capable of recognising and extracting key patterns and structures in data to enable reasoning and making data-driven decisions without human involvement. Machine Learning is extensively used in our day-to-day life without even being aware of it. Few such Machine Learning driven systems include Google Search refining and customising results, friends and products recommendation on social media, fare prediction when booking a taxi, virtual assistants such as Alexa, Siri and Google Now that learn our personal information and provide us customised service. Machine Learning has been a crucial component of our modern world which is helping a number engineering and other industries such as manufacturing, robotics and automation, self-driving vehicle technology, healthcare, financial services, retail etc.

This module aims to provide underlying mathematical, statistical and theoretical concepts of Machine Learning along with essential programming skills and expertise to design, build, and implement appropriate Machine Learning techniques for various engineering applications. The module introduces classical regression, classification and clustering models and modern deep learning models. The module includes relevant programming exercises to complement the theoretical concepts, which will allow students to gain valuable conceptual and programming skills to build, optimise and implement these models into a range of practical engineering challenges.

Outline Of Syllabus

Introduction of Machine Learning: Machine Learning Definition and Examples, Supervised Learning, Unsupervised Learning, Data Representation, Brief introduction of Regression, Classification and Clustering Methods

Review of Linear Algebra: Vectors and Matrices, Scalar Multiplication, Matrix-Vector Multiplication, Matrix Multiplication Properties, Inverse and Transpose, Eigenvalues and Eigenvectors

Machine Learning Basics: Gaussian Distribution, Hypothesis Testing, Decision Boundary, Maximum Likelihood Estimation, Overfitting, Regularisation, Bayesian Theorem, Cost Functions, Optimization methods, Univariate and Multivariate Gradient Descent

Classical Supervised Learning Algorithms: Linear Regression, Logistic Regression, Decision Tree, Support Vector Machine, Kernels, Random Forest, Naive Bays, K-nearest Neighbors

Classical Clustering Algorithms: K-Means Clustering, Expectation Maximisation

Modern Deep Learning Algorithms: Non-Linear Hypothesis, Neurons and the Brain, Artificial Neural Networks – Multilayer Perceptrons, Convolutional Neural Network, Recurrent Neural Network

Dimensionality Reduction (Feature Extraction) methods: Data Compression and Visualisation, Principal Component Analysis

Ethical Issues: Machine Learning Ethics, Legislation and Fairness; Societal Impact of Data Biases, Opacity and Bias in Decision Systems; Privacy, Anonymity and Surveillance; Impact, Security and Threats of Machine Learning Systems

Teaching Methods

Teaching Activities
Category Activity Number Length Student Hours Comment
Structured Guided LearningLecture materials300:3015:00Pre-recorded video lectures (Asynchronous online delivery).
Scheduled Learning And Teaching ActivitiesLecture41:004:00PiP discussions and Q&A sessions.
Scheduled Learning And Teaching ActivitiesLecture61:006:00Online synchronous discussions and Q&A sessions.
Guided Independent StudyAssessment preparation and completion111:0011:00Completion and review of formative assessment (online Quizzes)
Guided Independent StudyAssessment preparation and completion11:301:30Written exam.
Scheduled Learning And Teaching ActivitiesPractical52:0010:00PiP Computing Lab sessions for programming exercises.
Structured Guided LearningAcademic skills activities52:3012:30Asynchronous Practical: Completion of additional programming exercises
Guided Independent StudyIndependent study301:0030:00Lectures follow up: Reviewing lecture materials, building understanding and creating comments on pro
Guided Independent StudyIndependent study101:0010:00Revision for final exam
Total100:00
Teaching Rationale And Relationship

The module is delivered using mixture of teaching methods: asynchronous recorded lecture videos, scheduled in-person Q&A/discussion sessions and online synchronous sessions that cover theoretical foundations of Machine Learning. In addition, practical lab sessions provide opportunity to build, test and implement those Machine Learning concepts along with multiple programming exercises that will be issued throughout the course.

Assessment Methods

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

Exams
Description Length Semester When Set Percentage Comment
Written Examination902A50On-campus closed-book exam under normal circumstances otherwise off campus online exam
Other Assessment
Description Semester When Set Percentage Comment
Practical/lab report2M50Students will complete the set programming exercises to design and verify Machine learning models
Formative Assessments
Description Semester When Set Comment
Computer assessment2MStudents will complete online quizzes to check their understanding of the taught materials
Assessment Rationale And Relationship

he written exam primarily assesses students’ knowledge and understanding on fundamental Machine Learning principles. The online quizzes will be set up on each topic which will help students to review, analyse and check their knowledge on those Machine Learning concepts and strengthen their understanding. These quizzes will be released every week which will provide opportunity to students to check their understanding as they progress along with the course materials. In the scheduled computing labs, students will work on set programming tasks; students will be assessed on their practical skills (formulation, design, testing and analysis skills) on those exercises.

In the situation where in-person exam cannot take place, students will be issued 24-hr-take-home exam. The computing sessions and practical assessment will be also conducted online synchronously.

Reading Lists

Timetable