In this paper I assess the explanatory role of internal representations in connectionist models of cognition. Focusing on both the internal‘hidden’units and the connection weights between units, I argue that the standard reasons for viewing these components as representations are inadequate to bestow an explanatorily useful notion of representation. Hence, nothing would be lost from connectionist accounts of cognitive processes if we were to stop viewing the weights and hidden units as internal representations.

Contemporary epistemology has assumed that knowledge is represented in sentences or propositions. However, a variety of extensions and alternatives to this view have been proposed in other areas of investigation. We review some of these proposals, focusing on (1) Ryle's notion of knowing how and Hanson's and Kuhn's accounts of theory-laden perception in science; (2) extensions of simple propositional representations in cognitive models and artificial intelligence; (3) the debate concerning imagistic versus propositional representations in cognitive psychology; (4) recent treatments of (...) concepts and categorization which reject the notion of necessary and sufficient conditions; and (5) parallel distributed processing (connectionist) models of cognition. This last development is especially promising in providing a flexible, powerful means of representing information nonpropositionally, and carrying out at least simple forms of inference without rules. Central to several of the proposals is the notion that much of human cognition might consist in pattern recognition rather than manipulation of rules and propositions. (shrink)

In this paper I evaluate the soundness of the prototype paradigm, in particular its basic assumption that there are pan-human psychological essences or core meanings that refer to basic-level natural kinds, explaining why, on the whole, human communication and learning are successful. Instead I argue that there are no particular pan-human basic elements for thought, meaning and cognition, neither prototypes, nor otherwise. To illuminate my view I draw on examples from anthropology. More generally I argue that the prototype paradigm exemplifies (...) two assumptions that dominate cognitive science: (1) If human beings use words they mean something particular and what they mean can be discovered by scientific methods. (2) There is a fixed number of domains of categorization, each made up of a fixed number of basic categories. I suggest that these two assumptions lead to Brave New World. (shrink)

The introduction of connectionist or parallel distributed processing (PDP) systems to model cognitive functions has raised the question of the possible relations between these models and traditional information processing models which employ rules to manipulate representations. After presenting a brief account of PDP models and two ways in which they are commonly interpreted by those seeking to use them to explain cognitive functions, I present two ways one might relate these models to traditional information processing models and so not totally (...) repudiate the tradition of modelling cognition through systems of rules and representations. The proposal that seems most promising is that PDP-type structures might provide the underlying framework in which a rule and representation model might be implemented. To show how one might pursue such a strategy, I discuss recent research by Barsalou on the instability of concepts and show how that might be accounted for in a system whose microstructure had a PDP architecture. I also outline how adopting a multi-leveled view of the mind, where on one level the mind employed a PDP-type system and at another level constituted a rule processing system, would allow researchers to relocate some problems which seemed difficult to explain at one level, such as the capacity for concept learning, to another level where it could be handled in a straightforward manner. (shrink)

There is currently a debate over whether cognitive architecture is classical or connectionist in nature. One finds the following three comparisons between classical architecture and connectionist architecture made in the pro-connectionist literature in this debate: (1) connectionist architecture is neurally plausible and classical architecture is not; (2) connectionist architecture is far better suited to model pattern recognition capacities than is classical architecture; and (3) connectionist architecture is far better suited to model the acquisition of pattern recognition capacities by learning than (...) is classical architecture. If true, (1)–(3) would yield a compelling case against the view that cognitive architecture is classical, and would offer some reason to think that cognitive architecture may be connectionist. We first present the case for (1)–(3) in the very words of connectionist enthusiasts. We then argue that the currently available evidence fails to support any of (1)–(3). (shrink)

In this paper I assess the explanatory role of internal representations in connectionist models of cognition. Focusing on both the internal‘hidden’units and the connection weights between units, I argue that the standard reasons for viewing these components as representations are inadequate to bestow an explanatorily useful notion of representation. Hence, nothing would be lost from connectionist accounts of cognitive processes if we were to stop viewing the weights and hidden units as internal representations.

I defend two theses here. First, I argue that at least many of the commitments that Wittgenstein identifies as “hinge commitments” are plausibly what cognitive psychology and artificial intelligence call “procedural knowledge.” Procedural knowledge can be implemented in cognitive systems in a variety of ways, and these modes of implementation, I argue, predict several properties of Wittgensteinian hinge commitments, including their functional profile, as well as other of their characteristic features. Second, I argue that thinking of hinge commitments as a (...) kind of procedural knowledge allows a unified virtue-theoretic treatment of the generation of knowledge, the transmission of knowledge, and Wittgensteinian “hinge knowledge.” This last thesis is noteworthy, in that Wittgenstein and his defenders have so far failed to offer any unified epistemology of hinge commitments and the knowledge that such commitments are supposed to make possible. (shrink)

Abstract In rounded terms and modern dress a theory of intentionality is a theory about how humans take in information via the senses and in the very process of taking it in understand it and, most often, make subsequent use of it in guiding human behaviour. The problem of intentionality in this century has been the problem of providing an adequate explanation of how a purely physical causal system, the brain, can both receive information and at the same time understand (...) it, that is, to put it even more briefly, how a brain can have semantic content. In two articles, one in the previous number of the journal and this present one, I engage in a critical examination of the two most thoroughly canvassed approaches to the theory and problem of intentionality in philosophical psychology over the last 100 years. In the first article, subtitled ?The modern reduction of intentionality?, I examined the reductive approach pioneered by Carnap and reaching its apotheosis in the work of Daniel Dennett. In this second article, subtitled ?The return to representation?, I examine the approach which can be traced back to the work of Noam Chomsky but which has been given its canonical treatment in the work of Jerry Fodor. (shrink)