2020/21 Taught Postgraduate Module Catalogue

COMP5623M Artificial Intelligence

15 creditsClass Size: 300

Module manager: David Hogg
Email: d.c.hogg@leeds.ac.uk

Taught: Semester 2 (Jan to Jun) View Timetable

Year running 2020/21

Pre-requisite qualifications

For students on the CDT programme: COMP5712M Programming for Data Science

Pre-requisites

COMP5712M

Programming for Data Science

This module is mutually exclusive with

COMP5624M

Artificial Intelligence

This module is not approved as an Elective

Module summary

The module introduces the field of Artificial Intelligence (AI), taking a strongly integrative and state of the art approach based on deep neural networks. In line with the use of AI in key sectors (e.g. finance, health, law), there is an emphasis on the combination of multiple input modalities – specifically, combining images, text and structured data. Students gain hands-on experience in developing AI systems to address real-world problems, providing the knowledge and skills necessary to develop an AI system as part of an MSc project.

Objectives

To provide students with a state of the art understanding of AI, and highly practical skills and expertise in the construction of AI systems, including those that integrate multiple modalities.
To prepare students for a research degree involving innovation in the construction of AI systems.
To prepare students for a role in industry or the public-sector, where they may help to build, specify, recommend and critique AI systems.
To provide sufficient knowledge for students to be able to think creatively about possible AI solutions to real-world problems.
To gives students an understanding of the limitations of the state of the art and future research directions, including the need for causal explanations.

Learning outcomes
On completion of this module, students will be able to:
Design and implement AI systems in a language such as Python, based on machine learning;
Apply deep learning in standard AI tasks (e.g. image classification, sentiment analysis);
Represent data from various modalities (e.g. text, images, records) for multi-modal deep learning (e.g. translating images into textual captions, translating text into cognitive categories such as human sentiment);
Critically evaluate systems, using standard performance metrics;
Demonstrate an understanding of the current limitations of deep learning, the dependence on data and computational resources, and the challenge of causal explanation;
Apply their knowledge to address challenges from a specific sector; for example in detecting financial fraud from transaction data, and in informing medical diagnosis through combining medical images and structured data from electronic patient records.

Syllabus

Review of linear and nearest-neighbour classification, and k-means clustering.
Deep feed-forward neural networks, learning from data, and evaluation in standard tasks (e.g. classification).
Representations for images, audio, text and structured data.
Convolutional neural networks, autoencoder networks, generative adversarial networks, recursive networks, temporal convolutional networks.
Hands-on application of deep learning for the analysis of images, text and structured data.
Integration of different modalities.
Evaluation and performance metrics.
Deep networks and causal explanation.
Hands-on application depending on student specialism (e.g. finance, health, law), and using sector-specific datasets (e.g. credit-card transactions, pathology images).

Teaching methods

Delivery type	Number	Length hours	Student hours
Lecture	22	1.00	22.00
Practical	10	1.00	10.00
Private study hours			118.00
Total Contact hours			32.00
Total hours (100hr per 10 credits)			150.00

Private study

The student will design, build, train and evaluate several varieties of deep neural network models, some relating to their specialist domain (e.g. finance, health, law). Written reports from a subset of these exercises will form part of the formal assessment of the module.

Opportunities for Formative Feedback

Formative assessment will be coupled to the practical exercises in order to monitor student progress and provide feedback.

Methods of assessment

Coursework

Assessment type	Notes	% of formal assessment
In-course Assessment	Practical Exercise - Program development with DFN/ CNN	25.00
In-course Assessment	Practical Exercise - Program development multi-modality	25.00
In-course MCQ	MCQ/Short Answer Test (Gradescope)	25.00
In-course MCQ	MCQ/Short Answer Test (Gradescope)	25.00
Total percentage (Assessment Coursework)		100.00

This module will be reassessed by an online time-constrained assessment.

Reading list

The reading list is available from the Library website

Last updated: 18/02/2021 14:58:14

Disclaimer

Browse Other Catalogues

• Undergraduate module catalogue
• Taught Postgraduate module catalogue
• Undergraduate programme catalogue
• Taught Postgraduate programme catalogue

Errors, omissions, failed links etc should be notified to the Catalogue Team.PROD