Unit information: Advanced Methods in Artificial Intelligence in 2028/29

Unit name	Advanced Methods in Artificial Intelligence
Unit code	SEMT30008
Credit points	20
Level of study	H/6
Teaching block(s)	Teaching Block 2 (weeks 13 - 24)
Unit director	Dr. Hu
Open unit status	Not open
Units you must take before you take this one (pre-requisite units)	Methods of AI
Units you must take alongside this one (co-requisite units)	None
Units you may not take alongside this one	None
School/department	School of Engineering Mathematics and Technology
Faculty	Faculty of Engineering

Unit Information

Why is this unit important?

The term deep learning refers to neural network models (DNN) that are comprised of multiple layers allowing complex high-dimensional representation and processing and trained using very large data sets via back-propagation. This unit introduces a variety of deep neural network architectures and algorithms that underpin state-of-the-art approaches to machine learning applications in image processing, natural language processing and generative AI. These architectures lie at the heart of the modern revolution in machine learning and its deployment in a range of highly successful technologies. The unit will include aspects of mathematical underpinnings and students will also learn how to implement these approaches in specialist machine learning frameworks.

How does this unit fit into your programme of study

This unit provides a grounding in more advanced machine learning methods building on the introductory concepts and algorithms covered in years 1 & 2. It will also provide students with extensive hands-on experience of using state-of-the-art software frameworks and libraries. These are key tools for an AI engineer allowing them to understand and deploy machine learning technologies in diverse applications ranging from image processing, NLP and generative content creation.

Your learning on this unit

An overview of content

Topics covered in this unit will include:

• Deep learning architectures for computer vision tasks, including convolutional neural networks (CNNs), object detection, semantic segmentation, and image captioning.
• Explore deep learning architectures for natural language processing (NLP) tasks, including transformer-based models such as BERT and GPT, sequence-to-sequence models, attention mechanisms, and recurrent neural networks (RNNs)
• Representation learning (latent Spaces, embeddings)
• Generative networks; variational autoencoders, generative adversarial networks and their applications in generating realistic data and image-to-image translation
• Other advanced topics in machine learning such as timeseries analysis, forecasting & classification
• Comparison of DNN approaches with other advanced machine learning approaches such as kernel methods.

How will students, personally, be different as a result of the unit

Throughout this unit there will be a focus on students developing their skills using machine learning software libraries to implement deep learning. In combination with an understanding of the underpinning mathematics of different architecture this will mean that students are better equipped to tackle real-world problems using deep learning.

Learning outcomes

On successful completion of this unit, students will be able to:

1. Explain the mathematical underpinning or different deep learning architectures
2. Implement deep learning models using appropriate software libraries
3. Identify and implement deep learning architectures appropriate to different types of applications
4. Explain the representation of complex features and concepts in deep learning
5. Describe how generative AI can be used for content creation

How you will learn

Teaching will be delivered through a combination of synchronous and asynchronous sessions, including lectures and computer laboratory sessions.

How you will be assessed

Tasks which help you learn and prepare you for summative tasks (formative):

Computer laboratories will provide help and feedback on laboratory worksheets. Example worksheets will explore mathematical underpinning and feedback including worked solutions will support the exam.

Tasks which count towards your unit mark (summative):

This unit will be assessed by two assessments:

• A coursework requiring the implementation of deep learning architectures – ILOs 2 & 3 (50%)
• An in person exam – ILOs 1,4 & 5 (50%)

When assessment does not go to plan:

Re-assessment takes the same form as the original summative assessment. If you pass one of the summative assessments, then your mark for this can be carried forward towards your final mark and you will only have to be reassessed on the assessment that you did not pass.

Resources

If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.

If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. SEMT30008).

How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours of study to complete. Your total learning time is made up of contact time, directed learning tasks, independent learning and assessment activity.

See the University Workload statement relating to this unit for more information.

Assessment
The assessment methods listed in this unit specification are designed to enable students to demonstrate the named learning outcomes (LOs). Where a disability prevents a student from undertaking a specific method of assessment, schools will make reasonable adjustments to support a student to demonstrate the LO by an alternative method or with additional resources.

The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit. The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates within the Regulations and Code of Practice for Taught Programmes.