DEEP LEARNING AND ADVANCED AI - 2024/5

Module Overview

In recent years, AI has seen tremendous growth due in large part to more powerful computers, larger scale data and techniques to establish comprehensive framework through deeper neural networks. This module introduces a wide range of deep learning and the latest state of art techniques in AI for serving the world through innovation, understanding and compassion. Fundamental concepts on applied maths and establishment on effective learning objectives that thread through key elements in machine learning techniques will be discussed throughout the module. Students will study how to build suitable AI systems that can operate in complicated, real-world environments. The module also prepares students to explore further challenges and opportunities to work with advanced AI and bring them to new frontiers.

The module content will typically be updated each year reflecting the latest evolution in AI.

 

Module provider

Computer Science and Electronic Eng

Module Leader

TANG H Lilian (CS & EE)

Number of Credits: 15

ECTS Credits: 7.5

Framework: FHEQ Level 6

Module cap (Maximum number of students): N/A

Module Availability

Semester 2

Prerequisites / Co-requisites

COM2028 Introduction to Artificial Intelligence; background in Linear algebra, calculus, and probability.

Module content

Each year the module content will be updated to reflect the state of art in the field. Here is sample structure for 2024, subject to update annual

Attention and Transformers

• Fundamentals of Transformer architecture


• Understanding attention mechanisms


• Learning and inferencing

Transformer Families

• Exploring advanced Transformer models


• Practical applications of Transformers in various domains


• Recent advancements and variations in Transformer technology

Transformers in Vision and Beyond

• Vision Transformers


• Autoencoders, VAE, Masked Autoencoder (MAE)


• Contrastive Language–Image Pre-training

Generative Models

• Generative Adversarial Networks (GANs).


• Diffusion Models


• Multi-modality applications

Large Language Models (LLMs)

• In-depth exploration of Large Language Models.


• Understanding Models of Experts (MoE).


• Longer Context 

Large Multimodal Models (LMMs)

• Introduction to Visual Language Models.


• Integration of visual, textual, and other modality data.

Object Detection and Segmentation

• Classic and the latest progress

Self-Supervised Learning

• Self-supervised Learning


• Contrastive Learning

Further Topic

Assessment pattern

Alternative Assessment

N/A

Assessment Strategy

The assessment strategy is designed to provide students with the opportunity to demonstrate that they have achieved the module learning outcomes.

Thus, the summative assessment for this module consists of:

• 
  Coursework: deliverables will be in the form of a coursework project.
  


• 
  Unseen Examination
  

Formative assessment and feedback:

Students will be guided to work on lab exercises and assignments, and are encouraged to submit both  lab exercises and assignments regularly through SurreyLearn in order to receive individual feedback. Students will be able to complete the coursework project successfully once the foundation of the coursework is built through lab exercises and assignments as these will be supporting the coursework projects.

Individual Feedback on the coursework project will be given as soon as possible within two weeks or before the exam whichever is sooner. Students will be able to gauge their progress through regular feedback at different stages.

 

Module aims

• The module aims to show students the state of art in the field of Artificial Intelligence. It will cover a variety of approaches in the context of deep learning and demonstrate how to build intelligence systems for various practical applications.

Learning outcomes

Methods of Teaching / Learning

The module will develop analytical skills and the understanding of the subject area through:

• Lectures


• tutorials


• In-class discussion and presentations

The module will develop practical skills through:

• Lab exercises and assignments


• Coursework project

All activities will be co-ordinated via SurreyLearn.

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

https://readinglists.surrey.ac.uk
Upon accessing the reading list, please search for the module using the module code: COM3025

Other information

Digital Capabilities

Artificial Intelligence is one of the British government’s key strategy pillars. The advanced AI skills taught in this module provide students digital skills that are fundamental to solving many computer science problems today. Deep Learning is currently being used in many industries to solve problems such as speech recognition. The techniques learned in this module give student the theory and the practical experience to design and build systems that use these techniques to identify patterns in large datasets. These skills are highly valued in industry.

Employability

This module provides advanced AI, and software skills that are important in solving a many real-life problems today. The theoretical underpinning provides students with an understanding of how the algorithm works. The practical skills taught in labs and allow students to develop the Deep Learning solutions to problems. Students are equipped with practical problem-solving skills, theoretical skills, and mathematical and statistical skills, all of which are highly valuable to employers.

Global and Cultural Skills

Computer Science is a global language and the tools and languages used on this module can be used internationally. This module allows students to develop skills that will allow them to reason about and develop applications with global reach and collaborate with their peers around the world.

Resourcefulness and Resilience

This module involves practical problem-solving skills that teach a student how to reason about and solve new unseen problems through combining the theory taught with practical technologies for systems that are in everyday use. These problems often involve large and complex datasets and the techniques taught in this module will allow students to develop practical solutions to analyse these datasets using cutting edge techniques.

Programmes this module appears in

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2024/5 academic year.