• To equip students with the knowledge about basic algorithms that have been used to enable the AI agents to conduct the perception, inference, and planning tasks;
• To equip students with the knowledge about machine learning algorithms;
• To provide experience in applying basic AI algorithms to solve problems;
• To provide experience in applying machine learning algorithms to practical problems.

(LO1) Ability to explain in detail how the techniques in the perceive-inference-action loop work.

(LO2) Ability to choose, compare, and apply suitable basic learning algorithms to simple applications.

(LO3) Ability to explain how deep neural networks are constructed and trained, and apply deep neural networks to work with large scale datasets.

(LO4) Understand probabilistic graphical models, and is able to do probabilistic inference on the probabilistic graphical models.

(S1) Self-management (readiness to accept responsibility (i.e. leadership), flexibility, resilience, self-starting, appropriate assertiveness, time management, readiness to improve own performance based on feedback/reflective learning.)

(S2) Positive attitude (A 'can-do' approach, a readiness to take part and contribute; openness to new ideas and a drive to make these happen. Employers also value entrepreneurial graduates who demonstrate an innovative approach, creative thinking, bring fresh knowledge and challenge assumptions.)

(S3) Application of numeracy (manipulation of numbers, general mathematical awareness and its application in practical contexts (e.g. measuring, weighing, estimating and applying formulae))

(S4) Computer Science practice

Introduction (2 lectures): Introduction to the module and the Overview of Machine Learning.

Learning Basics (4 lectures): Learning Basics, Probability Foundation, Linear Algebra and Python

Traditional Machine Learning Algorithms (10 lectures): Decision Tree, k-nearest neighbour, Linear Regression, Gradient Descent, Naïve Bayes

Deep Learning Algorithms (6 lectures): Functional View, Features, Forward and Backward Training, Convolutional Neural Networks, Tensorflow, Model Evaluation

Probabilistic Graphical Models (6 lectures): Introduction, I-Maps, Reasoning Patterns, D-Separation, Structural Learning

Revision (1 lecture)

Advanced Topics (2 lectures, optional)

Teaching Method 1 - Lecture
Description:
Attendance Recorded: Not yet decided
Notes: 3 per week during semester

Teaching Method 2 - Laboratory Work
Description:
Attendance Recorded: Not yet decided

Standard on-campus delivery
Teaching Method 1 - Lecture
Description: Mix of on-campus/on-line synchronous/asynchronous sessions
Teaching Method 2 - Laboratory Work
Description: On-campus synchronous sessions