Brains, Gases and Robots

Over the past decade there has been renewed interest within AI in building simple autonomous ’creatures’ as a way of investigating mechanisms underlying the generation of adaptive behaviour [4, 1]. The vast majority of researchers in this field use some form of artificial neural network (ANN) as the basis of the ’nervous system’ of their agents. These networks can be envisaged as simple nodes connected together by directional wires along which signals flow. As has been pointed out by various people (e.g. [3]), advances in neuroscience have made it clear that the propagation of action potentials, and the changing of synaptic connection strengths, is only a very small part of the story of the brain (e.g [17]). This in turn means that connectionist style networks, and even recurrent dynamical ones, are generally very different kinds of systems from those that generate sophisticated adaptive behaviours in animals. Although our picture of biological neuronal networks changes every few years, contemporary neuroscience can provide a rich source of inspiration in devising alternative styles of artificial network [2].