production
Skip to Content

CS5079: APPLIED ARTIFICIAL INTELLIGENCE (2021-2022)

Last modified: 31 May 2022 13:05


Course Overview

This course will allow students to use cutting-edge AI technologies to investigate the creation and application of AI systems. Such tools include deep learning libraries and simulation environments.

Course Details

Study Type Postgraduate Level 5
Session First Sub Session Credit Points 15 credits (7.5 ECTS credits)
Campus Aberdeen Sustained Study No
Co-ordinators
  • Dr Bruno Yun

What courses & programmes must have been taken before this course?

  • Either Any Postgraduate Programme or Programme Level 5
  • Either Any Postgraduate Programme or Master of Engineering in Computing Science

What other courses must be taken with this course?

None.

What courses cannot be taken with this course?

None.

Are there a limited number of places available?

No

Course Description

The Applied AI course will give a firm grasp of AI, its applications, its challenges related to commercial, social, and regulatory aspects with real-world use cases. On completion of this course, students will be able to apply the theoretical and practical knowledge they have gained on previous modules to undertake several AI mini-projects. Each project will exercise AI application libraries (e.g., TensorFlow or Keras), and students will therefore understand how AI techniques e.g., classifier and neural network systems, reinforcement learning systems and simulation/evaluation systems, can be combined to create an end-to-end deployable AI solution. They will also be aware of the additional challenges an AI developer has to keep in mind, especially regarding the performance, decision accuracy, ethical, regulatory and social aspects. 


Contact Teaching Time

Information on contact teaching time is available from the course guide.

Teaching Breakdown

More Information about Week Numbers


Details, including assessments, may be subject to change until 31 August 2023 for 1st half-session courses and 22 December 2023 for 2nd half-session courses.

Summative Assessments

3x computer programming exercises

Assessment Type Summative Weighting 100
Assessment Weeks 10,11,12 Feedback Weeks 11,12,13

Look up Week Numbers

Feedback

These exercises will comprise three "mini-projects" evaluating student understanding of the material taught in the module. Each will address one of the topics taught in an application relevant way (e.g. programming a neural network, utilising enforcement learning for motion planning or simulating robot behaviour in a warehouse)

Learning Outcomes
Knowledge LevelThinking SkillOutcome
ConceptualApplyStudents will be able to document – in a reproducible manner – their approach to AI system construction.
ConceptualApplyStudents will be able to combine different components into an end-to-end solution.
ConceptualEvaluateStudents will be able to validate the effectiveness of their solution.
ConceptualUnderstandStudents will understand how libraries for AI system creation are applied and used in practice.
ReflectionAnalyseStudents will reflect on their new knowledge and apply it to a practical example.
ReflectionEvaluateStudents will be able to reflect and modify their design in response to validation of an AI system’s performance.

Formative Assessment

There are no assessments for this course.

Resit Assessments

Resubmission of failed individual assessment

Assessment Type Summative Weighting 100
Assessment Weeks Feedback Weeks

Look up Week Numbers

Feedback
Learning Outcomes
Knowledge LevelThinking SkillOutcome
ConceptualApplyStudents will be able to document – in a reproducible manner – their approach to AI system construction.
ConceptualApplyStudents will be able to combine different components into an end-to-end solution.
ConceptualEvaluateStudents will be able to validate the effectiveness of their solution.
ConceptualUnderstandStudents will understand how libraries for AI system creation are applied and used in practice.
ReflectionAnalyseStudents will reflect on their new knowledge and apply it to a practical example.
ReflectionEvaluateStudents will be able to reflect and modify their design in response to validation of an AI system’s performance.

Course Learning Outcomes

Knowledge LevelThinking SkillOutcome
ConceptualApplyStudents will be able to combine different components into an end-to-end solution.
ConceptualUnderstandStudents will understand how libraries for AI system creation are applied and used in practice.
ConceptualApplyStudents will be able to document – in a reproducible manner – their approach to AI system construction.
ReflectionEvaluateStudents will be able to reflect and modify their design in response to validation of an AI system’s performance.
ConceptualEvaluateStudents will be able to validate the effectiveness of their solution.
ReflectionAnalyseStudents will reflect on their new knowledge and apply it to a practical example.

Compatibility Mode

We have detected that you are have compatibility mode enabled or are using an old version of Internet Explorer. You either need to switch off compatibility mode for this site or upgrade your browser.