Writings Available On-Line
There are a number of things which I have written which are available on-line.
Just click on the appropriate link below to view each paper.
Comments and suggestions are always welcome. Please send them
- 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
- 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.