This advanced course teaches students about modern Artificial Intelligence techniques to address complex engineering problems. The course introduces modern techniques in artificial intelligence, including deep learning and reinforcement learning and provides an overview of advanced programming libraries in a variety of domains, including best practices in training and evaluating AI system.

■ 2-3h/week lectures weeks 1-7

■ 3h/week computer labs weeks 3-7

■ 3h/week lab weeks 8-10 (drop in)

■ Group project presentations week 11

none

none

Individual assessments:

- Individual report (20%) on strategy for solving a AI problem (identification appropriate framework and benchmarking)

Group assessment:

- Development, implementation, training and benchmarking AI algorithm for problem: presentation and practical demonstration (30%)

Final exam:

- 90 minute written exam (50%)

It is the default expectation that all courses will offer opportunities for reassessment or deferred assessment. Where it is not possible to offer this in some assessment components, the grade achieved at the first attempt will be counted towards the final course grade, and any exceptions for this course are described below.

[No exceptions]

This course aims to present students with modern techniques in artificial intelligence, including deep learning ad reinforcement learning, to address large multidimensional datasets and complex data.

The course will evaluate AI in the context of sustainability and responsible innovation. Specific aspects related to energy demand, computational cost and infrastructure impact of AI will be presented and discussed with the help of invited experts from the industry sector.

The course focusses on the application of AI techniques to engineering problems. The students will be introduced to the use of advanced libraries in a variety of domains as well as providing good practice in training and validating models.

The course will include practical AI case studies.

By the end of this course students will be able to:

■ Evaluate the impact of AI on our society, in terms of resources consumption and long-term sustainability of the solutions.

■ Design, build, train and apply fully connected deep neural networks to address a specific task.

■ Train agents to interact with a given environment using reinforcement learning algorithms

■ Determine and judge the strengths and weaknesses of various AI/ML algorithms and propose appropriate choices for specific problems.

■ Evaluate a complex engineering application and create a suitable AI-driven solution to address it.