| CODE | ICS3215 | |||||||||
| TITLE | AI and Adaptive Systems | |||||||||
| UM LEVEL | 03 - Years 2, 3, 4 in Modular Undergraduate Course | |||||||||
| MQF LEVEL | 6 | |||||||||
| ECTS CREDITS | 6 | |||||||||
| DEPARTMENT | Intelligent Computer Systems | |||||||||
| DESCRIPTION | The objectives of AI can be classified into two broad categories: engineering outcomes and scientific outcomes. On this view, the aims of AI centre on either implementing systems that have some particular useful characteristics (engineering) or understanding how those characteristics are implemented in natural systems (science). The interaction of these two motivations has been the primary driver in the development of AI. In the sixty plus years since the Dartmouth Conference the field of AI has expanded massively and great progress has been made. Yet still we struggle to build robots with the navigational capabilities of an ant or to give an AI system the kind of open-ended learning ability displayed by infant. This study-unit aims to give students a deeper understanding of adaptive systems in nature and to survey the current state of the art in artificial adaptive (i.e. intelligent) behaviour. Focussing on non-symbolic A.I., the study-unit will cover evolutionary (genetic) algorithms, artificial neural networks, situated and embodied approaches, and developmental cognitive robotics. An interdisciplinary approach will be taken with case studies of real-world adaptive problem-solving in animals and humans used to illustrate the AI techniques taught. Study-unit Aims: The study-unit will introduce students to this perspective on AI and enable them to develop an understanding of how natural intelligence can inspire the design of new synthetic systems and conversely, how such systems teach us about intelligent behaviour in nature. The study-unit will cover non-symbolic approaches to AI; The subsumption architecture; Ant algorithms; ALife; simulation methods; evolutionary robotics; neural networks; cognitive and developmental robotics and dynamical systems approaches to adaptive behaviour. Students will be introduced to embodied and enactive approaches to cognition and human-robot interaction (HRI) will be used as an application domain for the evaluation of the approaches and methodologies introduced in the study-unit. Learning Outcomes: 1. Knowledge & Understanding: By the end of the study-unit the student will be able to: - Describe and define non-symbolic techniques in AI. - Identify key principles of natural adaptive behaviour and explain how they inform the design of synthetic systems. - Explain the interdisciplinary nature of AI. 2. Skills: By the end of the study-unit the student will be able to: - Analyse and apply non-symbolic techniques to AI problems. - Analyse AI problems and formulate design strategies using appropriate techniques for different problem domains. - Formulate algorithms for the application of different non-symbolic techniques to a number of different problem domains. - Critique the different approaches and theoretical perspectives. - Design and carry out a research project and demonstrate the ability to organise their time in order to comply with the project specification. Main Text/s and any supplementary readings: There is no single book or resource which would form an appropriate set text for this study-unit therefore a set of core readings will be made available for download through the VLE. Supplementary material for the lectures will also be available via the VLE. |
|||||||||
| ADDITIONAL NOTES | Students taking this study-unit need to have a technical background. | |||||||||
| STUDY-UNIT TYPE | Lecture and Independent Study | |||||||||
| METHOD OF ASSESSMENT |
|
|||||||||
| LECTURER/S | ||||||||||
|
The University makes every effort to ensure that the published Courses Plans, Programmes of Study and Study-Unit information are complete and up-to-date at the time of publication. The University reserves the right to make changes in case errors are detected after publication.
The availability of optional units may be subject to timetabling constraints. Units not attracting a sufficient number of registrations may be withdrawn without notice. It should be noted that all the information in the description above applies to study-units available during the academic year 2025/6. It may be subject to change in subsequent years. |
||||||||||