Cookies on this website

We use cookies to ensure that we give you the best experience on our website. If you click 'Accept all cookies' we'll assume that you are happy to receive all cookies and you won't see this message again. If you click 'Reject all non-essential cookies' only necessary cookies providing core functionality such as security, network management, and accessibility will be enabled. Click 'Find out more' for information on how to change your cookie settings.

The human brain continuously processes data from the five senses: sight, hearing, smell, touch and taste. This chapter reviews the progress made in the past 20 years in the design of artificial cognitive systems that can process data from the first three of these senses i.e., sight, hearing, and smell. It then goes on to review the issue of "data fusion," the ability to combine disparate sensory data. This chapter focuses on the achievements of the traditional engineering or "IT-centric" approach. This relies on building mathematical models of artificial sensory systems that lay no claim to biological plausibility or relevance. This approach has reaped real dividends when applied to object recognition, visual tracking or speaker-independent continuous speech recognition. Although this approach has not been able to match natural sensory systems, it has achieved some impressive results. Furthermore, this chapter is tailored to promote the objective of the Foresight Cognitive Systems project. The aim of the project is to investigate ways in which the life sciences and physical sciences can learn from each other, either by working together or by greater understanding of recent progress in each others' areas of research. © 2006 Elsevier Ltd. All rights reserved.

Original publication





Book title

Cognitive Systems - Information Processing Meets Brain Science

Publication Date



85 - 104