1. To provide students with an introduction to key topics in the field of Artificial Intelligence (AI), including Machine Learning, Deep Learning, Natural Language Processing (NLP) and Computer Vision.
2. To present fundamental problems in all these areas and explain the common methods used to deal with these problems.
3. To develop the practical skills necessary to build AI applications using data from different domains.

(LO1) An in-depth understanding of key areas in applied machine learning.

(LO2) Ability to critically justify the use of Neural Network architectures and Deep Learning.

(LO3) Ability to apply state-of-the-art machine learning techniques to a variety of applications.

(LO4) Ability to critically evaluate the output of machine learning solutions.

(S1) Critical thinking and problem solving – Problem identification.

(S2) Critical thinking and problem solving – Critical analysis.

(S3) Creative thinking to develop appropriate solutions.

Machine Learning basics (2 weeks):
• Module introduction and AI / machine learning overview
• Fundamental elements: supervised and unsupervised learning, feature engineering, bias/variance issues, model performance evaluation metrics, hyperparameter tuning, etc.
• Introduction to software libraries available (e.g., keras, tensorflow, pyTorch, etc.)
Neural Networks architectures and Deep Learning (2 weeks):
• Neural networks overview
• Deep Learning models and software libraries’ capabilities on: convolutional neural networks, recurrent neural networks, generative adversarial networks, autoencoders, etc.
• Implementation of basic deep learning architectures for simple tasks.
Applications to Natural Language Processing (3 weeks):
• Natural Language Processing (NLP) overview
• Implementation of text classification or sentiment prediction methods using l ong-short term memory networks
Applications to Computer Vision and Image Understanding (3 weeks):
• Computer Vision overview
• Implementation of image classification/segmentation, object detection using convolutional networks.

Teaching Method 1 – Lecture
Description:
Attendance Recorded: Not yet decided
Notes: 3 lectures per week for 10 weeks

Teaching Method 2 – Laboratory Work
Description:
Attendance Recorded: Not yet decided
Notes: 1 lab session per week for 10 weeks

Due to Covid-19, in 2021/22, one or more of the following delivery methods will be implemented based on the current local conditions.
(a) Hybrid delivery
Teaching Method 1 - Lecture
Description: Mix of on-campus/on-line synchronous/asynchronous sessions
Teaching Method 2 - Laboratory Work
Description: Mix of on-campus/on-line synchronous/asynchronous sessions

(b) Fully online delivery and assessment
Teaching Method 1 - Lecture
Description: On-line synchronous/asynchronous lectures
Teaching Method 2 - Laboratory Work
Description: On-line synchronous/asynchronous sessions

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