Switch to: References
Citations of:
Connectionist Models and Their Properties
Cognitive Science 6 (3):205-254 (1982)
Add citations
You mustlogin to add citations.
| |
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) | |
Recent “connectionist” models provide a new explanatory alternative to the digital computer as a model for brain function. Evidence from our EEG research on the olfactory bulb suggests that the brain may indeed use computational mechanisms like those found in connectionist models. In the present paper we discuss our data and develop a model to describe the neural dynamics responsible for odor recognition and discrimination. The results indicate the existence of sensory- and motor-specific information in the spatial dimension of EEG (...) activity and call for new physiological metaphors and techniques of analysis. Special emphasis is placed in our model on chaotic neural activity. We hypothesize that chaotic behavior serves as the essential ground state for the neural perceptual apparatus, and we propose a mechanism for acquiring new forms of patterned activity corresponding to new learned odors. Finally, some of the implications of our neural model for behavioral theories are briefly discussed. Our research, in concert with the connectionist work, encourages a reevaluation of explanatory models that are based only on the digital computer metaphor. (shrink) | |
We outline a framework of multilevel neurocognitive mechanisms that incorporates representation and computation. We argue that paradigmatic explanations in cognitive neuroscience fit this framework and thus that cognitive neuroscience constitutes a revolutionary break from traditional cognitive science. Whereas traditional cognitive scientific explanations were supposed to be distinct and autonomous from mechanistic explanations, neurocognitive explanations aim to be mechanistic through and through. Neurocognitive explanations aim to integrate computational and representational functions and structures across multiple levels of organization in order to explain (...) cognition. To a large extent, practicing cognitive neuroscientists have already accepted this shift, but philosophical theory has not fully acknowledged and appreciated its significance. As a result, the explanatory framework underlying cognitive neuroscience has remained largely implicit. We explicate this framework and demonstrate its contrast with previous approaches. (shrink) | |
This target article presents a new computational theory of explanatory coherence that applies to the acceptance and rejection of scientific hypotheses as well as to reasoning in everyday life, The theory consists of seven principles that establish relations of local coherence between a hypothesis and other propositions. A hypothesis coheres with propositions that it explains, or that explain it, or that participate with it in explaining other propositions, or that offer analogous explanations. Propositions are incoherent with each other if they (...) are contradictory, Propositions that describe the results of observation have a degree of acceptability on their own. An explanatory hypothesis is acccpted if it coheres better overall than its competitors. The power of the seven principles is shown by their implementation in a connectionist program called ECHO, which treats hypothesis evaluation as a constraint satisfaction problem. Inputs about the explanatory relations are used to create a network of units representing propositions, while coherende and incoherence relations are encoded by excitatory and inbihitory links. ECHO provides an algorithm for smoothly integrating theory evaluation based on considerations of explanatory breadth, simplicity, and analogy. It has been applied to such important scientific cases as Lovoisier's argument for oxygen against the phlogiston theory and Darwin's argument for evolution against creationism, and also to cases of legal reasoning. The theory of explanatory coherence has implications for artificial intelligence, psychology, and philosophy. (shrink) | |
This paper presents a general computational treatment of how mammals are able to deal with visual objects and environments. The model tries to cover the entire range from behavior and phenomenological experience to detailed neural encodings in crude but computationally plausible reductive steps. The problems addressed include perceptual constancies, eye movements and the stable visual world, object descriptions, perceptual generalizations, and the representation of extrapersonal space.The entire development is based on an action-oriented notion of perception. The observer is assumed to (...) be continuously sampling the ambient light for information of current value. The central problem of vision is taken to be categorizing and locating objects in the environment. The critical step in this process is the linking of visual information to symbolic object descriptions; this is calledindexing, from the analogy of identifying a book from index terms. The system must also identifysituationsand use this knowledge to guide movement and other actions in the environment. The treatment focuses on the different representations of information used in the visual system.The four representational frames capture information in the following forms: retinotopic, head-based, symbolic, and allocentric. The functional roles of the four frames, the communication among them, and their suggested neurophysiological realization constitute the core of the paper. The model is perforce crude, but appears to be consistent with all relevant findings. (shrink) | |
Marr (1982) may have been one of the rst vision researchers to insist that in modeling vision it is important to separate the location of visual features from their type. He argued that in early stages of visual processing there must be “place tokens” that enable subsequent stages of the visual system to treat locations independent of what specic feature type was at that location. Thus, in certain respects a collinear array of diverse features could still be perceived as a (...) line, and under certain conditions could function as such in perceptual phenomena like the Poggendorf illusion. (shrink) | |
The general problem of visual search can be shown to be computationally intractable in a formal, complexity-theoretic sense, yet visual search is extensively involved in everyday perception, and biological systems manage to perform it remarkably well. Complexity level analysis may resolve this contradiction. Visual search can be reshaped into tractability through approximations and by optimizing the resources devoted to visual processing. Architectural constraints can be derived using the minimum cost principle to rule out a large class of potential solutions. The (...) evidence speaks strongly against bottom-up approaches to vision. In particular, the constraints suggest an attentional mechanism that exploits knowledge of the specific problem being solved. This analysis of visual search performance in terms of attentional influences on visual information processing and complexity satisfaction allows a large body of neurophysiological and psychological evidence to be tied together. (shrink) | |
This paper argues that a theory of situated vision, suited for the dual purposes of object recognition and the control of action, will have to provide something more than a system that constructs a conceptual representation from visual stimuli: it will also need to provide a special kind of direct (preconceptual, unmediated) connection between elements of a visual representation and certain elements in the world. Like natural language demonstratives (such as `this' or `that') this direct connection allows entities to be (...) referred to without being categorized or conceptualized. Several reasons are given for why we need such a preconcep- tual mechanism which individuates and keeps track of several individual objects in the world. One is that early vision must pick out and compute the relation among several individual objects while ignoring their properties. Another is that incrementally computing and updating representations of a dynamic scene requires keeping track of token individuals despite changes in their properties or locations. It is then noted that a mechanism meeting these requirements has already been proposed in order to account for a number of disparate empiri- cal phenomena, including subitizing, search-subset selection and multiple object tracking (Pylyshyn et al., Canadian Journal of Experimental Psychology 48(2) (1994) 260). This mechanism, called a visual index or FINST, is brie. (shrink) | |
Human agents draw a variety of inferences effortlessly, spontaneously, and with remarkable efficiency – as though these inferences were a reflexive response of their cognitive apparatus. Furthermore, these inferences are drawn with reference to a large body of background knowledge. This remarkable human ability seems paradoxical given the complexity of reasoning reported by researchers in artificial intelligence. It also poses a challenge for cognitive science and computational neuroscience: How can a system of simple and slow neuronlike elements represent a large (...) body of systemic knowledge and perform a range of inferences with such speed? We describe a computational model that takes a step toward addressing the cognitive science challenge and resolving the artificial intelligence paradox. We show how a connectionist network can encode millions of facts and rules involving n-ary predicates and variables and perform a class of inferences in a few hundred milliseconds. Efficient reasoning requires the rapid representation and propagation of dynamic bindings. Our model (which we refer to as SHRUTI) achieves this by representing (1) dynamic bindings as the synchronous firing of appropriate nodes, (2) rules as interconnection patterns that direct the propagation of rhythmic activity, and (3) long-term facts as temporal pattern-matching subnetworks. The model is consistent with recent neurophysiological evidence that synchronous activity occurs in the brain and may play a representational role in neural information processing. The model also makes specific psychologically significant predictions about the nature of reflexive reasoning. It identifies constraints on the form of rules that may participate in such reasoning and relates the capacity of the working memory underlying reflexive reasoning to biological parameters such as the lowest frequency at which nodes can sustain synchronous oscillations and the coarseness of synchronization. (shrink) | |
Computation and information processing are among the most fundamental notions in cognitive science. They are also among the most imprecisely discussed. Many cognitive scientists take it for granted that cognition involves computation, information processing, or both – although others disagree vehemently. Yet different cognitive scientists use ‘computation’ and ‘information processing’ to mean different things, sometimes without realizing that they do. In addition, computation and information processing are surrounded by several myths; first and foremost, that they are the same thing. In (...) this paper, we address this unsatisfactory state of affairs by presenting a general and theory-neutral account of computation and information processing. We also apply our framework by analyzing the relations between computation and information processing on one hand and classicism and connectionism on the other. We defend the relevance to cognitive science of both computation, in a generic sense that we fully articulate for the first time, and information processing, in three important senses of the term. Our account advances some foundational debates in cognitive science by untangling some of their conceptual knots in a theory-neutral way. By leveling the playing field, we pave the way for the future resolution of the debates’ empirical aspects. (shrink) | |
When cognitive neuropsychologists make inferences about the functional architecture of the normal mind from selective cognitive impairments they generally assume that the effects of brain damage are local, that is, that the nondamaged components of the architecture continue to function as they did before the damage. This assumption follows from the view that the components of the functional architecture are modular, in the sense of being informationally encapsulated. In this target article it is argued that this “locality” assumption is probably (...) not correct in general. Inferences about the functional architecture can nevertheless be made from neuropsychological data with an alternative set of assumptions, according to which human information processing is graded, distributed, and interactive. These claims are supported by three examples of neuropsychological dissociations and a comparison of the inferences obtained from these impairments with and without the locality assumption. The three dissociations are: selective impairments in knowledge of living things, disengagment of visual attention, and overt face recognition. In all three cases, the neuropsychological phenomena lead to more plausible inferences about the normal functional architecture when the locality assumption is abandoned. Also discussed are the relations between the locality assumption in neuropsychology and broader issues, including Fodor's modularity hypothesis and the choice between top-down and bottom-up research approaches. (shrink) | |
How do minds emerge from developing brains? According to the representational features of cortex are built from the dynamic interaction between neural growth mechanisms and environmentally derived neural activity. Contrary to popular selectionist models that emphasize regressive mechanisms, the neurobiological evidence suggests that this growth is a progressive increase in the representational properties of cortex. The interaction between the environment and neural growth results in a flexible type of learning: minimizes the need for prespecification in accordance with recent neurobiological evidence (...) that the developing cerebral cortex is largely free of domain-specific structure. Instead, the representational properties of cortex are built by the nature of the problem domain confronting it. This uniquely powerful and general learning strategy undermines the central assumption of classical learnability theory, that the learning properties of a system can be deduced from a fixed computational architecture. Neural constructivism suggests that the evolutionary emergence of neocortex in mammals is a progression toward more flexible representational structures, in contrast to the popular view of cortical evolution as an increase in innate, specialized circuits. Human cortical postnatal development is also more extensive and protracted than generally supposed, suggesting that cortex has evolved so as to maximize the capacity of environmental structure to shape its structure and function through constructive learning. (shrink) | |
The cerebral cortex is a rich and diverse structure that is the basis of intelligent behavior. One of the deepest mysteries of the function of cortex is that neural processing times are only about one hundred times as fast as the fastest response times for complex behavior. At the very least, this would seem to indicate that the cortex does massive amounts of parallel computation.This paper explores the hypothesis that an important part of the cortex can be modeled as a (...) connectionist computer that is especially suited for parallel problem solving. The connectionist computer uses a special representation, termed value unit encoding, that represents small subsets of parameters in a way that allows parallel access to many different parameter values. This computer can be thought of as computing hierarchies of sensorimotor invariants. The neural substrate can be interpreted as a commitment to data structures and algorithms that compute invariants fast enough to explain the behavioral response times. A detailed consideration of this model has several implications for the underlying anatomy and physiology. (shrink) | |
No categories | |
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) No categories | |
The posterior parietal cortex (PPC) is the most likely site where egocentric spatial relationships are represented in the brain. PPC cells receive visual, auditory, somaesthetic, and vestibular sensory inputs; oculomotor, head, limb, and body motor signals; and strong motivational projections from the limbic system. Their discharge increases not only when an animal moves towards a sensory target, but also when it directs its attention to it. PPC lesions have the opposite effect: sensory inattention and neglect. The PPC does not seem (...) to contain a “map” of the location of objects in space but a distributed neural network for transforming one set of sensory vectors into other sensory reference frames or into various motor coordinate systems. Which set of transformation rules is used probably depends on attention, which selectively enhances the synapses needed for making a particular sensory comparison or aiming a particular movement. (shrink) | |
This target article draws together two groups of experimental studies on the control of human movement through peripheral feedback and centrally generated signals of motor commands. First, during natural movement, feedback from muscle, joint, and cutaneous afferents changes; in human subjects these changes have reflex and kinesthetic consequences. Recent psychophysical and microneurographic evidence suggests that joint and even cutaneous afferents may have a proprioceptive role. Second, the role of centrally generated motor commands in the control of normal movements and movements (...) following acute and chronic deafferentation is reviewed. There is increasing evidence that subjects can perceive their motor commands under various conditions, but that this is inadequate for normal movement; deficits in motor performance arise when the reliance on proprioceptive feedback is abolished either experimentally or because of pathology. During natural movement, the CNS appears to have access to functionally useful input from a range of peripheral receptors as well as from internally generated command signals. The unanswered questions that remain suggest a number of avenues for further research. (shrink) | |
In my book How the Mind Works, I defended the theory that the human mind is a naturally selected system of organs of computation. Jerry Fodor claims that 'the mind doesn't work that way'(in a book with that title) because (1) Turing Machines cannot duplicate humans' ability to perform abduction (inference to the best explanation); (2) though a massively modular system could succeed at abduction, such a system is implausible on other grounds; and (3) evolution adds nothing to our understanding (...) of the mind. In this review I show that these arguments are flawed. First, my claim that the mind is a computational system is different from the claim Fodor attacks (that the mind has the architecture of a Turing Machine); therefore the practical limitations of Turing Machines are irrelevant. Second, Fodor identifies abduction with the cumulative accomplishments of the scientific community over millennia. This is very different from the accomplishments of human common sense, so the supposed gap between human cognition and computational models may be illusory. Third, my claim about biological specialization, as seen in organ systems, is distinct from Fodor's own notion of encapsulated modules, so the limitations of the latter are irrelevant. Fourth, Fodor's arguments dismissing of the relevance of evolution to psychology are unsound. (shrink) | |
No categories | |
Starting from Marr's ideas about levels of explanation, a theory of the data structures and access processes in human memory is demonstrated on 10 tasks. Functional characteristics of human memory are captured implementation-independently. Our theory generates a multidimensional task classification subsuming existing classifications such as the distinction between tasks that are implicit versus explicit, data driven versus conceptually driven, and simple associative (two-way bindings) versus higher order (threeway bindings), providing a broad basis for new experiments. The formal language clarifies the (...) binding problem in episodic memory, the role of input pathways in both episodic and semantic (lexical) memory, the importance of the input set in episodic memory, and the ubiquitous calculation of an intersection in theories of episodic and lexical access. (shrink) | |
The problems of access—retrieving linguistic structure from some mental grammar —and disambiguation—choosing among these structures to correctly parse ambiguous linguistic input—are fundamental to language understanding. The literature abounds with psychological results on lexical access, the access of idioms, syntactic rule access, parsing preferences, syntactic disambiguation, and the processing of garden‐path sentences. Unfortunately, it has been difficult to combine models which account for these results to build a general, uniform model of access and disambiguation at the lexical, idiomatic, and syntactic levels. (...) For example, psycholinguistic theories of lexical access and idiom access and parsing theories of syntactic rule access have almost no commonality in methodology or coverage of psycholinguistic data. This article presents a single probabilistic algorithm which models both the access and disambiguation of linguistic knowledge. The algorithm is based on a parallel parser which ranks constructions for access, and interpretations for disambiguation, by their conditional probability. Low‐ranked constructions and interpretations are pruned through beam‐search; this pruning accounts, among other things, for the garden‐path effect. I show that this motivated probabilistic treatment accounts for a wide variety of psycholinguistic results, arguing for a more uniform representation of linguistic knowledge and for the use of probabilistically‐enriched grammars and interpreters as models of human knowledge of and processing of language. (shrink) | |
Although the connectionist approach has lead to elegant solutions to a number of problems in cognitive science and artificial intelligence, its suitability for dealing with problems in knowledge representation and inference has often been questioned. This paper partly answers this criticism by demonstrating that effective solutions to certain problems in knowledge representation and limited inference can be found by adopting a connectionist approach. The paper presents a connectionist realization of semantic networks, that is, it describes how knowledge about concepts, their (...) properties, and the hierarchical relationship between them may be encoded as an interpreter‐free massively parallel network of simple processing elements that can solve an interesting class of inheritance and recognition problems extremely fast—in time proportional to the depth of the conceptual hierarchy. The connectionist realization is based on an evidential formulation that leads to principled solutions to the problems of exceptions and conflicting multiple inheritance situations during inheritance, and the best‐match or partial‐match computation during recognition. The paper also identifies constraints that must be satisfied by the conceptual structure in order to arrive at an efficient parallel realization. (shrink) | |
Connectionist models provide a promising alternative to the traditional computational approach that has for several decades dominated cognitive science and artificial intelligence, although the nature of connectionist models and their relation to symbol processing remains controversial. Connectionist models can be characterized by three general computational features: distinct layers of interconnected units, recursive rules for updating the strengths of the connections during learning, and “simple” homogeneous computing elements. Using just these three features one can construct surprisingly elegant and powerful models of (...) memory, perception, motor control, categorization, and reasoning. What makes the connectionist approach unique is not its variety of representational possibilities or its departure from explicit rule-based models, or even its preoccupation with the brain metaphor. Rather, it is that connectionist models can be used to explore systematically the complex interaction between learning and representation, as we try to demonstrate through the analysis of several large networks. (shrink) | |
No categories | |
No categories | |
states are to be understood in terms of their functional relationships to other mental states, not in terms of their material instantiation in any particular kind of hardware. But the argument that material instantiation is irrelevant to functional.. | |
Philosophy of science is positioned to make distinctive contributions to cognitive science by providing perspective on its conceptual foundations and by advancing normative recommendations. The philosophy of science I embrace is naturalistic in that it is grounded in the study of actual science. Focusing on explanation, I describe the recent development of a mechanistic philosophy of science from which I draw three normative consequences for cognitive science. First, insofar as cognitive mechanisms are information‐processing mechanisms, cognitive science needs an account of (...) how the representations invoked in cognitive mechanisms carry information about contents, and I suggest that control theory offers the needed perspective on the relation of representations to contents. Second, I argue that cognitive science requires, but is still in search of, a catalog of cognitive operations that researchers can draw upon in explaining cognitive mechanisms. Last, I provide a new perspective on the relation of cognitive science to brain sciences, one which embraces both reductive research on neural components that figure in cognitive mechanisms and a concern with recomposing higher‐level mechanisms from their components and situating them in their environments. (shrink) | |
The appropriate methodology for psychological research depends on whether one is studying mental algorithms or their implementation. Mental algorithms are abstract specifications of the steps taken by procedures that run in the mind. Implementational issues concern the speed and reliability of these procedures. The algorithmic level can be explored only by studying across-task variation. This contrasts with psychology's dominant methodology of looking for within-task generalities, which is appropriate only for studying implementational issues.The implementation-algorithm distinction is related to a number of (...) other “levels” considered in cognitive science. Its realization in Anderson's ACT theory of cognition is discussed. Research at the algorithmic level is more promising because it is hard to make further fundamental scientific progress at the implementational level with the methodologies available. Protocol data, which are appropriate only for algorithm-level theories, provide a richer source than data at the implementational level. Research at the algorithmic level will also yield more insight into fundamental properties of human knowledge because it is the level at which significant learning transitions are defined.The best way to study the algorithmic level is to look for differential learning outcomes in pedagogical experiments that manipulate instructional experience. This provides control and prediction in realistically complex learning situations. The intelligent tutoring paradigm provides a particularly fruitful way to implement such experiments.The implications of this analysis for the issue of modularity of mind, the status of language, research on human/computer interaction, and connectionist models are also examined. (shrink) | |
It is proposed to conceive of representation as an emergent phenomenon that is supervenient on patterns of activity of coarsely tuned and highly redundant feature detectors. The computational underpinnings of the outlined concept of representation are (1) the properties of collections of overlapping graded receptive fields, as in the biological perceptual systems that exhibit hyperacuity-level performance, and (2) the sufficiency of a set of proximal distances between stimulus representations for the recovery of the corresponding distal contrasts between stimuli, as in (...) multidimensional scaling. The present preliminary study appears to indicate that this concept of representation is computationally viable, and is compatible with psychological and neurobiological data. (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) | |
This paper introduces a special issue of Cognitive Science initiated on the 25th anniversary of the publication of Parallel Distributed Processing (PDP), a two-volume work that introduced the use of neural network models as vehicles for understanding cognition. The collection surveys the core commitments of the PDP framework, the key issues the framework has addressed, and the debates the framework has spawned, and presents viewpoints on the current status of these issues. The articles focus on both historical roots and contemporary (...) developments in learning, optimality theory, perception, memory, language, conceptual knowledge, cognitive control, and consciousness. Here we consider the approach more generally, reviewing the original motivations, the resulting framework, and the central tenets of the underlying theory. We then evaluate the impact of PDP both on the field at large and within specific subdomains of cognitive science and consider the current role of PDP models within the broader landscape of contemporary theoretical frameworks in cognitive science. Looking to the future, we consider the implications for cognitive science of the recent success of machine learning systems called “deep networks”—systems that build on key ideas presented in the PDP volumes. (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) |
Home |New books and articles |Bibliographies |Philosophy journals |About PhilPapers |API |Contact us |Code of conduct
PhilPapers logo byAndrea Andrews andMeghan Driscoll.
This site uses cookies and Google Analytics (see ourterms & conditions for details regarding the privacy implications).Use of this site is subject toterms & conditions.
All rights reserved byThe PhilPapers Foundation
Server: philpapers-web-54b44b69b7-g6h22 uwo