Writings Available On-Line

• What is AI? This link will take you to a thing I wrote for the E-zine The Scoop. It is basically a popularist piece. However, it gives an easy to read introduction to Artificial Intelligence. In addition, there are loads of links associated with the writing which are accessible on the footnotes. These links include classic papers and documents, important people, software available on the web and descriptions of classic AI systems.

• Connectionism Reconsidered: Minds, Machines and Models Abstract: In this paper the issue of drawing inferences about biological cognitive systems on the basis of connectionist simulations is addressed. In particular, the justification of inferences based on connectionist models trained using the backpropagation learning algorithm is examined. First it is noted that a justification commonly found in the philosophical literature is inapplicable. Then some general issues are raised about the relationships between models and biological systems. A way of conceiving the role of hidden units in connectionist networks is then introduced. This, in combination with an assumption about the way evolution goes about solving problems, is then used to suggest a means of justifying inferences about biological systems based on connectionist research.
• What the #$*%! is a Subsymbol? Abstract: In 1988, Smolensky proposed that connectionist processing systems should be understood as operating at what he termed the 'subsymbolic' level. Subsymbolic systems should be understood by comparing them to symbolic systems, in Smolensky's view. Up until recently, there have been real problems with analyzing and interpreting the operation of connectionist systems which have undergone training. However, recently published work on a network trained on a set of logic problems originally studied by Bechtel and Abrahamsen (1991)seems to offer the potential to provide a detailed, empirically based answer to questions about the nature of subsymbols. In this paper, I discuss the network analysis procedure and the results obtained using it. This provides the basis for a number of insights into the nature of subsymbols, which are perhaps surprising. Note: The diagrams in this paper have not converted properly to HTML.

• Some Myths of Connectionism. This paper considers a number of claims about connectionist systems which are often encoutered in the philosophical literature. The myths discussed here include the claim that connectionist systems are, in some sense, biological or neural, the calim that connectionist systems are compatible with real-time processing constraints, the claim that connectionist systems exhibit graceful degradation and the claim that connectionist systems are good generalizers. In the case of each of these claims, it is argued that there is a mythical component and, as such, claims of this kind should not be accepted by philosophers without appropriate qualification.

• A Revisionist History of Connectionism An alternative perspective on the history of connectionism is offered in this short paper. In this paper a number of claims and conclusions often encountered in standard versions of the hisatory are disputed. This paper also includes some new material from the people involved in the history of AI and Cognitive Science.

• An Introduction to Connectionism. This is a reasonably accessible introduction to the basic components and concepts which are important to connectionist systems. It includes a description of some of the kinds of processing units which can be employed.

• A Cognitive Science Bibliography

• Gilbert Ryle and The Chinese Sceptic: Do Epistemologists Need To Know How To? Abstract: Traditionally, epistemology has been concerned with the problems and questions which arise with propositional knowledge. This, however, is not the only way in which knowledge can be conceived. Propositional knowledge consists in an agent, s knowing that p, where p is some proposition. However, knowledge claims may also be made with respect to s's knowing how to q. In this case, q is some skill or action, and need not be straight forwardly propositional in nature. In this paper I will be mainly concerned with working out the ramifications of Ryle's (1949) conclusion, that 'knowing how to' cannot be reduced to a special case of 'knowing that'. I will also discuss the relationship between the two kinds of knowledge. Finally, I will indicate, following Hansen (1981 & 1983), that there are grounds for believing that the problems presented by the traditional philosophical skeptic do not arise with their usual force with respect to claims about s's knowing how to q, although alternative forms of scepticism may be applicable.