The article criticises the attempt to establish connectionism as an alternative theory of human cognitive architecture through the introduction of the
symbolic/subsymbolic distinction (Smolensky, 1988). The reasons for the introduction of this distinction are discussed and found to be unconvincing. It is shown that the
brittleness problem has been solved for a large class of
symbolic learning systems, e.g. the class of
top-down induction of decision-trees (
TDIDT) learning systems. Also, the process of articulating expert knowledge in rules seems quite practical for many important domains, including common sense knowledge.
The article discusses several experimental comparisons betweenTDIDT systems and artificial neural networks using the error backpropagation algorithm (ANNs usingBP). The properties of one of theTDIDT systemsID3 (Quinlan, 1986a) are examined in detail. It is argued that the differences in performance betweenANNs usingBP andTDIDT systems reflect slightly different inductive biases but are not systematic; these differences do not support the view that symbolic and subsymbolic systems are fundamentally incompatible. It is concluded, that thesymbolic/subsymbolic distinction is spurious. It cannot establish connectionism as an alternative cognitive architecture.
Key words Connectionism - symbolic/subsymbolic distinction - TDIDT (top-down induction of decision trees) - ID3 - Smolensky - Fodor - Pylyshyn - Quinlan