In “Connectionism and the fats of folk psychology”, Forster and Saidel argue that the central claim of Ramsey, Stich and Garon (1991)—that distributed connectionist models are incompatible with the causal discreteness of folk psychology—is mistaken. To establish their claim, they offer an intriguing model which allegedly shows how distributed representations can function in a causally discrete manner. They also challenge our position regarding projectibility of folk psychology. In this essay, I offer a response to their account and (...) show how their model fails to demonstrate that our original argument was mistaken. While I will discuss several difficulties with their model, my primary criticism will be that the features of their model that are causally discrete are not truly distributed, while the features that are distributed are not really discrete. Concerning the issue of projectibility, I am more inclined to agree with Forster and Saidel and I offer a revised account of what we should have said originally. (shrink)

There are many conflicting views concerning the nature of distributed representation, its compatibility or otherwise with symbolic representation, and its importance in characterizing the nature of connectionist models and their relationship to more traditional symbolic approaches to understanding cognition. Many have simply assumed that distribution is merely an implementation issue, and that symbolic mechanisms can be designed to take advantage of the virtues of distribution if so desired. Others, meanwhile, see the use of distributed representation as marking a (...) fundamental difference between the two approaches. One reason for this diversity of opinion is the fact that the relevant notions - especially that of. (shrink)

There has been much interest in the possibility of connectionist models whose representations can be endowed with compositional structure, and a variety of such models have been proposed. These models typically use distributed representations that arise from the functional composition of constituent parts. Functional composition and decomposition alone, however, yield only an implementation of classical symbolic theories. This paper explores the possibility of moving beyond implementation by exploiting holistic structure-sensitive operations on distributed representations. An experiment (...) is performed using Pollack’s Recursive Auto-Associative Memory. RAAM is used to construct distributed representations of syntactically structured sentences. A feed-forward network is then trained to operate directly on these representations, modeling syn- tactic transformations of the represented sentences. Successful training and generalization is obtained, demonstrating that the implicit structure present in these representations can be used for a kind of structure-sensitive processing unique to the connectionist domain. (shrink)

A number of examples are given of how localist models may incorporate distributed representations, without the types of nonlocal interactions that often render distributed models implausible. The need to analyze the information that is encoded by these representations is also emphasized as a metatheoretical constraint on model plausibility.

We focus on two components of Page's argument in favour of localist representations in connectionist networks: First, we take issue with the claim that localist representations can give rise to generalisation and show that whenever generalisation occurs, distributed representations are involved. Second, we counter the alleged shortcomings of distributed representations and show that their properties are preferable to those of localist approaches.

This paper is a revised and extended version of a keynote contribution to a recent conference on Cognitive Informatics. It offers a brief summary of some of the core concerns of other contributions to the conference, highlighting the range of issues under discussion; and argues that many of the central concepts and preoccupations of cognitive informatics as understood by participants--and others in the general field of computation--rely on ill-founded realist assumptions, and what has been termed the functionalist view of representation. (...) Even if such ideas--albeit in a revised form -- can be defended, there must be a more extensive engagement with the literature and issues outside the confines of the computing and computational orthodoxy. (shrink)

This paper is a revised and extended version of a keynote contribution to a recent conference on Cognitive Informatics. It offers a brief summary of some of the core concerns of other contributions to the conference, highlighting the range of issues under discussion; and argues that many of the central concepts and preoccupations of cognitive informatics as understood by participants--and others in the general field of computation--rely on ill-founded realist assumptions, and what has been termed the functionalist view of representation. (...) Even if such ideas--albeit in a revised form -- can be defended, there must be a more extensive engagement with the literature and issues outside the confines of the computing and computational orthodoxy. (shrink)

Distributed representations can be distributed in very many ways. The specific choice of representation for a specific model is based on considerations unique to the area of study. General statements about the effectiveness of distributed models are therefore of little value. The popularity of these models is discussed, particularly with respect to reporting conventions.

Bifurcation analysis of a real-time implementation of an ART network, which is functionally similar to the generalized localist model discussed in Page's manifesto shows that it yields a phase transition from local to distributed representation owing to continuous variation of the range of inhibitory connections. Hence there appears to be a qualitative dichotomy between local and distributed representations at the level of connectionistic networks conceived of as instances of nonlinear dynamical systems.

In this article we propose a theoretical framework of distributed representations and a methodology of representational analysis for the study of distributed cognitive tasks—tasks that require the processing of information distributed across the internal mind and the external environment. The basic principle of distributed representations Is that the representational system of a distributed cognitive task is a set of internal and external representations, which together represent the abstract structure of the task. The (...) basic strategy of representational analysis is to decompose the representation of a hierarchical task into its component levels so that the representational properties at each level can be independently examined. The theoretical framework and the methodology are used to analyze the hierarchical structure of the Tower of Hanoi problem. Based on this analysis, four experiments are designed to examine the representational properties of the Tower of Hanoi. Finally, the nature of external representations is discussed. (shrink)

This article describes a representation-based framework of distributed cognition. This framework considers distributed cognition as a cognitive system whose structures and processes are distributed between internal and external representations, across a group of individuals, and across space and time. The major issue for distributed research, under this framework, are the distribution, transformation, and propagation of information across the components of the distributed cognitive system and how they affect the performance of the system as a (...) whole. To demonstrate the value of this representation-based approach, the framework was used to describe and explain an important, challenging, and controversial issue — the concept of affordance. (shrink)

This article describes a representation-based framework of distributed cognition. This framework considers distributed cognition as a cognitive system whose structures and processes are distributed between internal and external representations, across a group of individuals, and across space and time. The major issue for distributed research, under this framework, are the distribution, transformation, and propagation of information across the components of the distributed cognitive system and how they affect the performance of the system as a (...) whole. To demonstrate the value of this representation-based approach, the framework was used to describe and explain an important, challenging, and controversial issue — the concept of affordance. (shrink)

Distributed Cognition and Integrational Linguistics have much in common. Both approaches see communicative activity and intelligent behaviour in general as strongly con- text-dependent and action-oriented, and brains as permeated by history. But there is some ten- sion between the two frameworks on three important issues. The majority of theorists of distributed cognition want to maintain some notions of mental representation and computa- tion, and to seek generalizations and patterns in the various ways in which creatures like us couple (...) with technologies, media, and other agents; many also want to offer explanations at subpersonal levels which may undercut the autonomy of personal-level accounts. In contrast, dominant views in integrational linguistics reject all invocation of representation, resist the explanatory search for similarity across contexts and moments, and see linguistics as a lay dis- cipline which should not offer explanations in terms alien to ordinary agents. On each of these issues, I argue that integrationists could move closer to the distributed cognition frame- work without losing the most important aspects of their view: integrationist criticisms of mainstream or classical theories can be respected while alliances with revised cognitivist views about representation, context, and explanation are developed. Ó 2004 Elsevier Ltd. All rights reserved. (shrink)

been to define various notions of distribution in terms of represented by one and the same distributed pattern (Mur- structures of correspondence between the represented items dock 1979). For example, it is standard in feedforward and the representational resources (e.g., van Gelder 1992). connectionist networks for one and the same set of synap- This approach may be misguided; the essence of this alter- tic weights to represent many associations between input native category of representation might be some other prop- (...) and output. erty entirely. For example, Haugeland (1991) has suggested • Equipotentiality In some cases, an item is represented by. (shrink)

By a lattice we shall always mean a distributive lattice which is bounded, i.e. has both a bottom element 0 and a top element 1. Lattice homomorphisms will always be assumed to preserve 0 and 1.

We continue work of our earlier paper :219–241, 2009) where abstract logics and particularly intuitionistic abstract logics are studied.logics can be topologized in a direct and natural way. This facilitates a topological study of classes of concrete logics whenever they are given in abstract form. Moreover, such a direct topological approach avoids the often complex algebraic and lattice-theoretic machinery usually applied to represent logics. Motivated by that point of view, we define in this paper the category of intuitionistic abstract logics (...) with stable logic maps as morphisms, and the category of implicative spectral spaces with spectral maps as morphisms. We show the equivalence of these categories and conclude that the larger categories of distributive abstract logics and distributive sober spaces are equivalent, too. (shrink)

The problem of representing the spatial structure of images, which arises in visual object processing, is commonly described using terminology borrowed from propositional theories of cognition, notably, the concept of compositionality. The classical propositional stance mandates representations composed of symbols, which stand for atomic or composite entities and enter into arbitrarily nested relationships. We argue that the main desiderata of a representational system—productivity and systematicity—can (indeed, for a number of reasons, should) be achieved without recourse to the classical, proposition‐like (...) compositionality. We show how this can be done, by describing a systematic and productive model of the representation of visual structure, which relies on static rather than dynamic binding and uses coarsely coded rather than atomic shape primitives. (shrink)

The problem of representing the spatial structure of images, which arises in visual object processing, is commonly described using terminology borrowed from propositional theories of cognition, notably, the concept of compositionality. The classical propositional stance mandates representations composed of symbols, which stand for atomic or composite entities and enter into arbitrarily nested relationships. We argue that the main desiderata of a representational system — productivity and systematicity — can (indeed, for a number of reasons, should) be achieved without recourse (...) to the classical, proposition-like compositionality. We show how this can be done, by describing a systematic and productive model of the representation of visual structure, which relies on static rather than dynamic binding and uses coarsely coded rather than atomic shape primitives. (shrink)

Fodor’s radical concept nativism flowed from his view that hypothesis testing is the only route to concept acquisition. Many have successfully objected to the overly-narrow restriction to learning by hypothesis testing. Existing representations can be connected to a new representational vehicle so as to constitute a sustaining mechanism for a new representation, without the new representation thereby being constituted by or structured out of the old. This paper argues that there is also a deeper objection. Connectionism shows that a (...) more fundamental assumption underpinning the debate can also be rejected: the assumption that the development of a new representation must be explained in content-involving terms if innateness is to be avoided. -/- Fodor has argued that connectionism offers no new resources to explain concept acquisition: unless it is merely an uninteresting claim about neural implementation, connectionism’s defining commitment to distributed representations reduces to the claim that some representations are structured out of others (which is the old, problematic research programme). Examination of examples of representational development in connectionist networks shows, however, that some such models explain the development of new representational capacities in non-representational terms. They illustrate the possibility of representational development that is not explicable-by-content. Connectionist representations can be distributed in an important sense, which is incompatible with the assumption of explanation-by-content: they can be distributed over non-representational resources that account for their development. Rejecting the assumption of explanation-by-content thereby opens up a more radical way of rejecting Fodor’s argument for radical concept nativism. (shrink)

Abstract Since their inception, distributional models of semantics have been criticized as inadequate cognitive theories of human semantic learning and representation. A principal challenge is that the representations derived by distributional models are purely symbolic and are not grounded in perception and action; this challenge has led many to favor feature-based models of semantic representation. We argue that the amount of perceptual and other semantic information that can be learned from purely distributional statistics has been underappreciated. We compare the (...) representations of three feature-based and nine distributional models using a semantic clustering task. Several distributional models demonstrated semantic clustering comparable with clustering-based on feature-based representations. Furthermore, when trained on child-directed speech, the same distributional models perform as well as sensorimotor-based feature representations of children’s lexical semantic knowledge. These results suggest that, to a large extent, information relevant for extracting semantic categories is redundantly coded in perceptual and linguistic experience. Detailed analyses of the semantic clusters of the feature-based and distributional models also reveal that the models make use of complementary cues to semantic organization from the two data streams. Rather than conceptualizing feature-based and distributional models as competing theories, we argue that future focus should be on understanding the cognitive mechanisms humans use to integrate the two sources. (shrink)

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)

Regular polysemes are sets of ambiguous words that all share the same relationship between their meanings, such as CHICKEN and LOBSTER both referring to an animal or its meat. To probe how a distributional semantic model, here exemplified by bidirectional encoder representations from transformers (BERT), represents regular polysemy, we analyzed whether its embeddings support answering sense analogy questions similar to “is the mapping between CHICKEN (as an animal) and CHICKEN (as a meat) similar to that which maps between LOBSTER (...) (as an animal) to LOBSTER (as a meat)?” We did so using the LRcos model, which combines a logistic regression classifier of different categories (e.g., animal vs. meat) with a measure of cosine similarity. We found that (a) the model was sensitive to the shared structure within a given regular relationship; (b) the shared structure varies across different regular relationships (e.g., animal/meat vs. location/organization), potentially reflective of a “regularity continuum;” (c) some high-order latent structure is shared across different regular relationships, suggestive of a similar latent structure across different types of relationships; and (d) there is a lack of evidence for the aforementioned effects being explained by meaning overlap. Lastly, we found that both components of the LRcos model made important contributions to accurate responding and that a variation of this method could yield an accuracy boost of 10% in answering sense analogy questions. These findings enrich previous theoretical work on regular polysemy with a computationally explicit theory and methods, and provide evidence for an important organizational principle for the mental lexicon and the broader conceptual knowledge system. (shrink)

Pessoa et al. (1998a) summarize a wide body of data suggesting that perceptual filling-in phenomena can be attributed to neural filling-in processes. However, they reject, on philosophical grounds, the hypothesis that filled-in representations in the brain are the immediate substrate of visual percepts. It is proposed in this commentary that resonant binding between distributed cortical areas may instead be the crucial ingredient for conscious visual percepts, and that filling-in processes may facilitate the interactions between behaving organisms and object (...) surfaces. These suggestions circumvent some of the philosophical problems associated with the idea of localized visual representations. (shrink)

Cognitive scientists have long used distributional semantic representations of categories. The predominant approach uses distributional representations of category‐denoting nouns, such as “city” for the category city. We propose a novel scheme that represents categories as prototypes over representations of names of its members, such as “Barcelona,” “Mumbai,” and “Wuhan” for the category city. This name‐based representation empirically outperforms the noun‐based representation on two experiments (modeling human judgments of category relatedness and predicting category membership) with particular improvements for (...) ambiguous nouns. We discuss the model complexity of both classes of models and argue that the name‐based model has superior explanatory potential with regard to concept acquisition. (shrink)

The human conceptual system comprises simulated information of sensorimotor experience and linguistic distributional information of how words are used in language. Moreover, the linguistic shortcut hypothesis predicts that people will use computationally cheaper linguistic distributional information where it is sufficient to inform a task response. In a pre‐registered category production study, we asked participants to verbally name members of concrete and abstract categories and tested whether performance could be predicted by a novel measure of sensorimotor similarity (based on an 11‐dimensional (...) representation of sensorimotor strength) and linguistic proximity (based on word co‐occurrence derived from a large corpus). As predicted, both measures predicted the order and frequency of category production but, critically, linguistic proximity had an effect above and beyond sensorimotor similarity. A follow‐up study using typicality ratings as an additional predictor found that typicality was often the strongest predictor of category production variables, but it did not subsume sensorimotor and linguistic effects. Finally, we created a novel, fully grounded computational model of conceptual activation during category production, which best approximated typical human performance when conceptual activation was allowed to spread indirectly between concepts, and when candidate category members came from both sensorimotor and linguistic distributional representations. Critically, model performance was indistinguishable from typical human performance. Results support the linguistic shortcut hypothesis in semantic processing and provide strong evidence that both linguistic and grounded representations are inherent to the functioning of the conceptual system. All materials, data, and code are available at https://osf.io/vaq56/. (shrink)