Introduction to Connectionist Modelling of Cognitive Processes

Introduction to Connectionist Modelling of Cognitive Processes

Introduction to Connectionist Modelling of Cognitive Processes

Introduction to Connectionist Modelling of Cognitive Processes


Connectionism is a way of modelling how the brain uses streams of sensory inputs to understand the world and produce behaviour, based on cognitive processes which actually occur. This book describes the principles, and their application to explaining how the brain produces speech, forms memories and recognises faces, how intellect develops, and how it deteriorates after brain damage. Part I explores the basic concepts, the architecture and properties of the most common connectionist models, and how connectionist learning rules work. Part II describes and evaluates connectionist models of a variety of cognitive processes, including the learning and production of speech, the formation of episodic memories and visual representations, the development of cognitive processes in infancy, and their breakdown in brain-damaged patients. The models range from some well-known classics to others at the frontiers of current research. Each chapter ends with a list of recommended further reading. Also included is a disk with the software for running tlearn, a user-friendly simulator for connectionist modelling of cognitive processes, which will run on either PCs or Macs. The software includes exercises to introduce the simulator, and working copies to explore some of the models described in the text. A reference handbook for tlearn is included to enable readers to build their own models. The authors, as well as being leading researchers in their field, have extensive experience of teaching connectionism to undergraduates. They have written the first comprehensive, up-to-date textbook on connectionist modelling, designed specifically for advanced undergraduates, and accessible to those with only limited knowledge of mathematics. This will be an essential introductory text for all students in psychology or cognitive science taking a course on connectionism.


From dust I rise And out of Nothing now awake; A stranger here Strange things doth meet, strange Glory see, But that they mine should be who Nothing was, That Strangest is of all, yet brought to pass.

Thomas Traherne (1684-1728)

The brain of the newborn child contains billions of neurons but the child can perform virtually no cognitive functions. After a few years, receiving continuous streams of signals from the outside world via its sensory surfaces, it can see, understand language, and control the movements of its body. The brain has discovered, without being taught, how to make sense of the signals arriving from the eyes and ears. 300 years ago Thomas Traherne realised the extraordinary nature of this untutored transformation from chaos to comprehension. The aim of cognitive science is to answer his question: How is it brought to pass?

What is the problem?

As adults we can see, walk and understand speech without conscious effort, and we have no memory of a time when we could not. Nor can we remember the process by which we learnt to do these tasks. So perhaps it is difficult to imagine that there is any problem in learning to see or to understand speech. To see how extraordinary this achievement is, consider what the infant must do to recognise words in continuous speech. If spoken words were presented in isolation and each example of a word was the same, as it is in print, it might not be too difficult for a child to discover that these units were significant. But this is far from the case. Words in speech do not come with gaps around them. You hear isolated words because you recognise the words which the speaker used. But in the original signal the sound patterns for most words run into each other without breaks. The separation of the speech stream into successive words is a construction of your speech recognition . . .

Search by... Author
Show... All Results Primary Sources Peer-reviewed


An unknown error has occurred. Please click the button below to reload the page. If the problem persists, please try again in a little while.