An intelligent system is a computer-based system that can represent, reason about, and interpret data. In doing so it can learn about the structure of the data, analyse the data to extract patterns and meaning, derive new information, and identify strategies and behaviours to act on the results of its analysis.
Intelligent systems come in many forms and have many applications, from processing huge data sets to controlling robots and drones. The ideas and concepts are drawn from the areas of artificial intelligence, machine learning, and a range of fields such as psychology, linguistics and brain sciences, forming many interdisciplinary relationships.
This minor provides a thorough introduction to intelligent systems, starting with the core building blocks and moving through to the more advanced areas of machine learning and neural networks. There will be particular emphasis on robotic systems, and how they can use machine learning to navigate and carry out complex tasks.
The teaching is led by staff from the UCL Computer Science Intelligent Systems Research Group, and by staff from the Virtual Environments and Computer Graphics Research Group specialising in robotic systems.
Module 1 (Year 2, Term 2) – Cognitive Systems and Intelligent Technologies
This module introduces the science and engineering of intelligent systems, including the correspondence with natural cognitive systems and the design of smart tools. It will cover the foundational theories, methods, and technologies involved in artificial intelligence and in cognitive systems science. Students will learn about the theoretical and technical challenges involved in modelling and building systems that can reason, solve problems, acquire and use knowledge, make decisions, and communicate in natural language. They will learn how intelligence in artificial systems and natural systems compares and contrasts, and about the smart technologies that extend human intelligence.
Module 2 (Year 3, Term 1) – Machine Learning and Neural Computation
The goals of the module are:
- to introduce neural computing as a knowledge acquisition and representation paradigm, to explain its basic principles and their relationship to neurobiological models, and to describe a range of neural computing techniques and their application areas;
- to introduce a range of modern machine learning methodologies, chiefly those that have been derived from, or are related to, neural computing paradigms, such as support vector machines and deep learning.
Students will develop a critical understanding of these approaches to artificial intelligence, covering both their strengths and potential weaknesses. They will also gain an ability to identify problems that can be tackled most effectively by neurally-based or machine learning solutions, and to select an appropriate learning methodology for the problem at hand.
Module 3 (Year 3, Term 1) – Robotic Systems
This module will introduce the core ideas and concepts in the design of software for controlling robots or drones, with the emphasis on navigation, route planning, obstacle avoidance, decision making, autonomous behaviour and image recognition. A range of hardware and sensor configurations will be considered, along with the use of simulators for software development and experimentation.
Students will develop a good understanding of how the science and engineering of intelligent systems can be applied to the design and control of robotic systems. The course will have a strong practical element where students will develop and apply software-based solutions for a range of problems.
Dr Simon Julier
Dept Computer Science
For further information contact
Dr. Graham Roberts
Dept Computer Science
Choose your minor
Please select your preferred minor via IEP Minors Moodle Poll.