Page argues convincingly for several important properties of localist representations in connectionist models of cognition. I argue that another important property of localist representations is that they serve as the starting point for connectionist representations of symbolic (relational) structures because they express meaningful properties independent of one another and their relations.

This paper explores the difference between Connectionist proposals for cognitive a r c h i t e c t u r e a n d t h e s o r t s o f m o d e l s t hat have traditionally been assum e d i n c o g n i t i v e s c i e n c e . W e c l a i m t h a t t h (...) e m a j o r d i s t i n c t i o n i s t h a t , w h i l e b o t h Connectionist and Classical architectures postulate representational mental states, the latter but not the former are committed to a symbol-level of representation, or to a ‘language of thought’: i.e., to representational states that have combinatorial syntactic and semantic structure. Several arguments for combinatorial structure in mental representations are then reviewed. These include arguments based on the ‘systematicity’ of mental representation: i.e., on the fact that cognitive capacities always exhibit certain symmetries, so that the ability to entertain a given thought implies the ability to entertain thoughts with semantically related contents. We claim that such arguments make a powerful case that mind/brain architecture is not Connectionist at the cognitive level. We then consider the possibility that Connectionism may provide an account of the neural (or ‘abstract neurological’) structures in which Classical cognitive architecture is implemented. We survey a n u m b e r o f t h e s t a n d a r d a r g u m e n t s t h a t h a v e b e e n o f f e r e d i n f a v o r o f Connectionism, and conclude that they are coherent only on this interpretation. (shrink)

Although the mechanics of how the eye works are well understood, debate still exists as to how the complex machinery of the brain interprets neural impulses...

Choice Outstanding Academic Title, 1996. In hundreds of articles by experts from around the world, and in overviews and "road maps" prepared by the editor, The Handbook of Brain Theory and Neural Networks charts the immense progress made in recent years in many specific areas related to great questions: How does the brain work? How can we build intelligent machines? While many books discuss limited aspects of one subfield or another of brain theory and neural networks, the Handbook covers the (...) entire sweep of topics—from detailed models of single neurons, analyses of a wide variety of biological neural networks, and connectionist studies of psychology and language, to mathematical analyses of a variety of abstract neural networks, and technological applications of adaptive, artificial neural networks. Expository material makes the book accessible to readers with varied backgrounds while still offering a clear view of the recent, specialized research on specific topics. (shrink)

Over the last decade, fully distributed models have become dominant in connectionist psychological modelling, whereas the virtues of localist models have been underestimated. This target article illustrates some of the benefits of localist modelling. Localist models are characterized by the presence of localist representations rather than the absence of distributed representations. A generalized localist model is proposed that exhibits many of the properties of fully distributed models. It can be applied to a number of problems that are difficult for fully (...) distributed models, and its applicability can be extended through comparisons with a number of classic mathematical models of behaviour. There are reasons why localist models have been underused, though these often misconstrue the localist position. In particular, many conclusions about connectionist representation, based on neuroscientific observation, can be called into question. There are still some problems inherent in the application of fully distributed systems and some inadequacies in proposed solutions to these problems. In the domain of psychological modelling, localist modelling is to be preferred. Key Words: choice; competition; connectionist modelling; consolidation; distributed; localist; neural networks; reaction-time. (shrink)

ACT is compared with a particular type of connectionist model that cannot handle symbols and use nonbiological operations which do not learn in real time. This focus continues an unfortunate trend of straw man debates in cognitive science. Adaptive Resonance Theory, or ART-neural models of cognition can handle both symbols and subsymbolic representations, and meet the Newell criteria at least as well as connectionist models.

First published in 1995, The Visual Brain in Action remains a seminal publication in the cognitive sciences. It presents a model for understanding the visual processing underlying perception and action, proposing a broad distinction within the brain between two kinds of vision: conscious perception and unconscious 'online' vision. It argues that each kind of vision can occur quasi-independently of the other, and is separately handled by a quite different processing system. In the 11 years since publication, the book has provoked (...) considerable interest and debate - throughout both cognitive neuroscience and philosophy, while the field has continued to flourish and develop. -/- For this new edition, the text from the original edition has been left untouched, standing as a coherent statement of the authors' position. However, a very substantial epilogue has been added to the book in which Milner and Goodale review some of the key developments that support or challenge the views that were put forward in the first edition. The new chapter summarizes developments in various relevant areas of psychology, neuroscience and behaviour. It notably supplements the main text by updating the reader on the contributions that have emerged from the use of functional neuroimaging, which was in its infancy when the first edition was written. Neuroimaging, and functional MRI in particular, has revolutionized the field over the past 11 years by allowing investigators to plot in detail the patterns of activity within the visual brains of behaving and perceiving humans. The authors show how its use now allows scientists to test and confirm their proposals, based as they then were largely on evidence accrued from primate neuroscience in conjunction with studies of neurological patients. (shrink)

Berkeley [Minds Machines 10 (2000) 1] described a methodology that showed the subsymbolic nature of an artificial neural network system that had been trained on a logic problem, originally described by Bechtel and Abrahamsen [Connectionism and the mind. Blackwells, Cambridge, MA, 1991]. It was also claimed in the conclusion of this paper that the evidence was suggestive that the network might, in fact, count as a symbolic system. Dawson and Piercey [Minds Machines 11 (2001) 197] took issue with this latter (...) claim. They described some lesioning studies that they argued showed that Berkeley’s (2000) conclusions were premature. In this paper, these lesioning studies are replicated and it is shown that the effects that Dawson and Piercey rely upon for their argument are merely an artifact of a threshold function they chose to employ. When a threshold function much closer to that deployed in the original studies is used, the significant effects disappear. (shrink)

PDP networks that use nonmonotonic activation functions often produce hidden unit regularities that permit the internal structure of these networks to be interpreted (Berkeley et al., 1995; McCaughan, 1997; Dawson, 1998). In particular, when the responses of hidden units to a set of patterns are graphed using jittered density plots, these plots organize themselves into a set of discrete stripes or bands. In some cases, each band is associated with a local interpretation. On the basis of these observations, Berkeley (2000) (...) has suggested that these bands are both subsymbolic and symbolic in nature, and has used the analysis of one network to support the claim that there are fewer differences between symbols and subsymbols than one might expect. We suggest below that this conclusion is premature. First, in many cases the local interpretation of each band is difficult to relate to the interpretation of a network's response; a more appropriate relationship only emerges when a band associated with one hidden unit is considered in the context of other bands associated with other hidden units (i.e., interpretations of distributed representations are more useful than interpretations of local representations). Second, the content that a band designates to an external observer (i.e., the interpretation assigned to a band by the researcher) can be quite different from the content that a band designates to the output units of the network itself.. We use two different network simulations – including the one described by Berkeley (2000) – to illustrate these points. We conclude that current evidence involving interpretations of nonmonotonic PDP networks actually illustrates the differences between symbolic and subsymbolic processing. (shrink)

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.Higher-level analyses of these connectionist models reveal subtle relations to symbolic models. Parallel connectionist memory and linguistic processes are hypothesized to give rise to processes that are describable at a higher level as sequential rule application. At the lower level, computation has the character of massively parallel satisfaction of soft numerical constraints; at the higher level, this can lead to competence characterizable by hard rules. Performance will typically deviate from this competence since behavior is achieved not by interpreting hard rules but by satisfying soft constraints. The result is a picture in which traditional and connectionist theoretical constructs collaborate intimately to provide an understanding of cognition. (shrink)

Much of the progress in the fields constituting cognitive science has been based upon the use of explicit information processing models, almost exclusively patterned after conventional serial computers. An extension of these ideas to massively parallel, connectionist models appears to offer a number of advantages. After a preliminary discussion, this paper introduces a general connectionist model and considers how it might be used in cognitive science. Among the issues addressed are: stability and noise‐sensitivity, distributed decision‐making, time and sequence problems, and (...) the representation of complex concepts. (shrink)