A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts consciously used to describe the task domain. The level of analysis is intermediate between those of symbolic cognitive models (...) and neural models. The explanations of behavior provided are like those traditional in the physical sciences, unlike the explanations provided by symbolic models. (shrink)

Many people have argued that the evolution of the human language faculty cannot be explained by Darwinian natural selection. Chomsky and Gould have suggested that language may have evolved as the by-product of selection for other abilities or as a consequence of as-yet unknown laws of growth and form. Others have argued that a biological specialization for grammar is incompatible with every tenet of Darwinian theory – that it shows no genetic variation, could not exist in any intermediate forms, confers (...) no selective advantage, and would require more evolutionary time and genomic space than is available. We examine these arguments and show that they depend on inaccurate assumptions about biology or language or both. Evolutionary theory offers clear criteria for when a trait should be attributed to natural selection: complex design for some function, and the absence of alternative processes capable of explaining such complexity. Human language meets these criteria: Grammar is a complex mechanism tailored to the transmission of propositional structures through a serial interface. Autonomous and arbitrary grammatical phenomena have been offered as counterexamples to the position that language is an adaptation, but this reasoning is unsound: Communication protocols depend on arbitrary conventions that are adaptive as long as they are shared. Consequently, language acquisition in the child should systematically differ from language evolution in the species, and attempts to analogize them are misleading. Reviewing other arguments and data, we conclude that there is every reason to believe that a specialization for grammar evolved by a conventional neo-Darwinian process. (shrink)

Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory. In this approach, hidden unit patterns are fed back to themselves: (...) the internal representations which develop thus reflect task demands in the context of prior internal states. A set of simulations is reported which range from relatively simple problems (temporal version of XOR) to discovering syntactic/semantic features for words. The networks are able to learn interesting internal representations which incorporate task demands with memory demands: indeed, in this approach the notion of memory is inextricably bound up with task processing. These representations reveal a rich structure, which allows them to be highly context‐dependent, while also expressing generalizations across classes of items. These representations suggest a method for representing lexical categories and the type/token distinction. (shrink)

Memory. There may be nothing more important to human beings than our ability to enshrine experience and recall it. While philosophers and poets have elevated memory to an almost mystical level, psychologists have struggled to demystify it. Now, according to Daniel Schacter, one of the most distinguished memory researchers, the mysteries of memory are finally yielding to dramatic, even revolutionary, scientific breakthroughs. Schacter explains how and why it may change our understanding of everything from false memory to Alzheimer's disease, from (...) recovered memory to amnesia with fascinating firsthand accounts of patients with striking—and sometimes bizarre—amnesias resulting from brain injury or psychological trauma. (shrink)

A provocative assessment of human thought and behavior, reissued with a new afterword, explores a range of conundrums from the ability of the mind to perceive three dimensions to the nature of consciousness, in an account that draws on ...

The performance of symbolic inference tasks has long been a challenge to connectionists. In this paper, we present an extended survey of this area. Existing connectionist inference systems are reviewed, with particular reference to how they perform variable binding and rule- based reasoning and whether they involve distributed or localist representations. The bene®ts and disadvantages of different representations and systems are outlined, and conclusions drawn regarding the capabilities of connectionist inference systems when compared with symbolic inference systems or when used (...) for cognitive modelling. q 2001 Elsevier Science Ltd. All rights reserved. (shrink)

As Ruben notes, the macrostrategy can allow that the distinction may also be drawn at some micro level, but it insists that descent to the micro level is ...

DCPS is a connectionist production system interpreter that uses distributed representations. As a connectionist model it consists of many simple, richly interconnected neuron‐like computing units that cooperate to solve problems in parallel. One motivation for constructing DCPS was to demonstrate that connectionist models are capable of representing and using explicit rules. A second motivation was to show how “coarse coding” or “distributed representations” can be used to construct a working memory that requires far fewer units than the number of different (...) facts that can potentially be stored. The simulation we present is intended as a detailed demonstration of the feasibility of certain ideas and should not be viewed as a full implementation of production systems. Our current model only has a few of the many interesting emergent properties that we eventually hope to demonstrate: It is damage‐resistant, it performs matching and variable binding by massively parallel constraint satisfaction, and the capacity of its working memory is dependent on the similarity of the items being stored. (shrink)

This paper critically examines the claim that parallel distributed processing (PDP) networks are autonomous learning systems. A PDP model of a simple distributed associative memory is considered. It is shown that the 'generic' PDP architecture cannot implement the computations required by this memory system without the aid of external control. In other words, the model is not autonomous. Two specific problems are highlighted: (i) simultaneous learning and recall are not permitted to occur as would be required of an autonomous system; (...) (ii) connections between processing units cannot simultaneously represent current and previous network activation as would be required if learning is to occur. Similar problems exist for more sophisticated networks constructed from the generic PDP architecture. We argue that this is because these models are not adequately constrained by the properties of the functional architecture assumed by PDP modelers. It is also argued that without such constraints, PDP researchers cannot claim to have developed an architecture radically different from that proposed by the Classical approach in cognitive science. (shrink)