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)

In this classic, the world's expert on language and mind lucidly explains everything you always wanted to know about language: how it works, how children learn it, how it changes, how the brain computes it, and how it evolved. With deft use of examples of humor and wordplay, Steven Pinker weaves our vast knowledge of language into a compelling story: language is a human instinct, wired into our brains by evolution. The Language Instinct received the William James Book Prize from (...) the American Psychological Association and the Public Interest Award from the Linguistics Society of America. This edition includes an update on advances in the science of language since The Language Instinct was first published. (shrink)

Chomsky proposes a reformulation of the theory of transformational generative grammar that takes recent developments in the descriptive analysis of particular ...

Noam Chomsky's book on syntactic structures is a serious attempts on the part of a linguist to construct within the tradition of scientific theory-construction ...

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)

On the occasion of a first conference on Cognitive Science, it seems appropriate to review the basis of common understanding between the various disciplines. In my estimate, the most fundamental contribution so far of artificial intelligence and computer science to the joint enterprise of cognitive science has been the notion of a physical symbol system, i.e., the concept of a broad class of systems capable of having and manipulating symbols, yet realizable in the physical universe. The notion of symbol so (...) defined is internal to this concept, so it becomes a hypothesis that this notion of symbols includes the symbols that we humans use every day of our lives. In this paper we attempt systematically, but plainly, to lay out the nature of physical symbol systems. Such a review is in ways familiar, but not thereby useless. Restatement of fundamentals is an important exercise. (shrink)

A young scientist and mathematician explores the mystery and complexity of human thought processes from an interdisciplinary point of view.

The term ‘emergence’ often causes confusion in science and philosophy, as it is used to express at least two quite different concepts. We can label these concepts _strong_ _emergence_ and _weak emergence_. Both of these concepts are important, but it is vital to keep them separate.

1 Cognitive Architectures 2 Multilayer Perceptrons 3 Relations between Variables 4 Structured Representations 5 Individuals 6 Where does the Machinery of Symbol Manipulation Come From? 7 Conclusions.

When the whole is greater than the sum of the parts--indeed, so great that the sum far transcends the parts and represents something utterly new and different--we call that phenomenon emergence. When the chemicals diffusing in the primordial waters came together to form the first living cell, that was emergence. When the activities of the neurons in the brain result in mind, that too is emergence. In The Emergence of Everything, one of the leading scientists involved in the study of (...) complexity, Harold J. Morowitz, takes us on a sweeping tour of the universe, a tour with 28 stops, each one highlighting a particularly important moment of emergence. For instance, Morowitz illuminates the emergence of the stars, the birth of the elements and of the periodic table, and the appearance of solar systems and planets. We look at the emergence of living cells, animals, vertebrates, reptiles, and mammals, leading to the great apes and the appearance of humanity. He also examines tool making, the evolution of language, the invention of agriculture and technology, and the birth of cities. And as he offers these insights into the evolutionary unfolding of our universe, our solar system, and life itself, Morowitz also seeks out the nature of God in the emergent universe, the God posited by Spinoza, Bruno, and Einstein, a God Morowitz argues we can know through a study of the laws of nature. Written by one of our wisest scientists, The Emergence of Everything offers a fascinating new way to look at the universe and the natural world, and it makes an important contribution to the dialogue between science and religion. (shrink)

Computing Methodologies -- Artificial Intelligence.

The Linguistic Review 24, 347-401 (2007).

What is the interaction between storage and computation in language processing? What is the psychological status of grammatical rules? What are the relative strengths of connectionist and symbolic models of cognition? How are the components of language implemented in the brain? The English past tense has served as an arena for debates on these issues. We defend the theory that irregular past-tense forms are stored in the lexicon, a division of declarative memory, whereas regular forms can be computed by a (...) concatenation rule, which requires the procedural system. Irregulars have the psychological, linguistic and neuropsychological signatures of lexical memory, whereas regulars often have the signatures of grammatical processing. Furthermore, because regular inflection is rule-driven, speakers can apply it whenever memory fails. (shrink)

Dynamical Grammar explores the consequences for language acquisition, language evolution, and linguistic theory of taking the underlying architecture of the language faculty to be that of a complex adaptive dynamical system. It contains the first results of a new and complex model of language acquisition which the authors have developed to measure how far language input is reflected in language output and thereby get a better idea of just how far the human language faculty is hard-wired.

What is the interaction between storage and computation in language processing? What is the psychological status of grammatical rules? What are the relative strengths of connectionist and symbolic models of cognition? How are the components of language implemented in the brain? The English past tense has served as an arena for debates on these issues. We defend the theory that irregular past-tense forms are stored in the lexicon, a division of declarative memory, whereas regular forms can be computed by a (...) concatenation rule, which requires the procedural system. Irregulars have the psychological, linguistic and neuropsychological signatures of lexical memory, whereas regulars often have the signatures of grammatical processing. Furthermore, because regular inflection is rule-driven, speakers can apply it whenever memory fails. (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)

Evidence from functional neuroimaging of the human brain indicates that information about salient properties of an object¿such as what it looks like, how it moves, and how it is used¿is stored in sensory and motor systems active when that information was acquired. As a result, object concepts belonging to different categories like animals and tools are represented in partially distinct, sensory- and motor property-based neural networks. This suggests that object concepts are not explicitly represented, but rather emerge from weighted activity (...) within property-based brain regions. However, some property-based regions seem to show a categorical organization, thus providing evidence consistent with category-based, domain-specific formulations as well.Acronyms and DefinitionsBiological motion: motion of animate agents characterized by highly flexible, fully articulated motion vectors, in contrast to the rigid, unarticulated motion vectors associated with most tools.Category-specific disorder: a relatively greater impairment in retrieving information about members of one superordinate object category (e.g., animals) as compared with other categories following brain injury or diseaseIPS: intraparietal sulcusLO: lateral occipital cortexObject concept: memory representations of a class or category of objects. Necessary for numerous cognitive functions including identifying an object as a member of a specific category and drawing inferences about object propertiespMTG: posterior middle temporal gyruspSTS: posterior superior temporal sulcusRepetition suppression: decreased neural response associated with repeated presentation of an identical, or a semantically/conceptually related, stimulusSD: semantic dementiaSemantic memory: a large division of long-term memory containing knowledge about the world including facts, ideas, beliefs, and conceptsSemantic priming: a short-lasting facilitation in processing a stimulus due to the prior presentation of a semantically related stimulusTMS: transcranial magnetic stimulationVPMC: ventral premotor cortex. (shrink)

Most theories of memory suggest that when we learn or memorize something, some drepresentation of that something is constructed, stored and later retrieved. This raises questions like:How is information represented?How is it stored?How is it retrieved?Then, how is it used?This paper tries to deal with all these at once. When you get an idea and want to “remember” it, you create a “K‐line” for it. When later activated, the K‐line induces a partial mental state resembling the one that created it. (...) A “partial mental state” is a subset of those mental agencies operating at one moment. This view leads to many ideas about the development, structure and physiology of memory, and about how to implement framelike representations in a distributed processor. (shrink)

A fundamental claim associated with parallel distributed processing theories of cognition is that knowledge is coded in a distributed manner in mind and brain. This approach rejects the claim that knowledge is coded in a localist fashion, with words, objects, and simple concepts, that is, coded with their own dedicated representations. One of the putative advantages of this approach is that the theories are biologically plausible. Indeed, advocates of the PDP approach often highlight the close parallels between distributed representations learned (...) in connectionist models and neural coding in brain and often dismiss localist theories as biologically implausible. The author reviews a range a data that strongly challenge this claim and shows that localist models provide a better account of single-cell recording studies. The author also contrast local and alternative distributed coding schemes and argues that common rejection of grandmother cell theories in neuroscience is due to a misunderstanding about how localist models behave. The author concludes that the localist representations embedded in theories of perception and cognition are consistent with neuroscience; biology only calls into question the distributed representations often learned in PDP models. (shrink)