Although connectionism is advocated by its proponents as an alternative to the classical computational theory of mind, doubts persist about its _computational_ credentials. Our aim is to dispel these doubts by explaining how connectionist networks compute. We first develop a generic account of computation—no easy task, because computation, like almost every other foundational concept in cognitive science, has resisted canonical definition. We opt for a characterisation that does justice to the explanatory role of computation in cognitive science. Next we (...) examine what might be regarded as the “conventional” account of connectionist computation. We show why this account is inadequate and hence fosters the suspicion that connectionist networks aren’t genuinely computational. Lastly, we turn to the principal task of the paper: the development of a more robust portrait of connectionist computation. The basis of this portrait is an explanation of the representational capacities of connection weights, supported by an analysis of the weight configurations of a series of simulated neural networks. (shrink)

Recently, connectionist models have been developed that seem to exhibit structuresensitive cognitive capacities without executing a program. This paper examines one such model and argues that it does execute a program. The argument proceeds by showing that what is essential to running a program is preserving the functional structure of the program. It has generally been assumed that this can only be done by systems possessing a certain temporalcausal organization. However, counterfactualpreserving functional architecture can be instantiated in other ways, (...) for example geometrically, which are realizable by connectionist networks. (shrink)

Shastri & Ajjanagadde argue convincingly that both structured connectionist networks and parallel dynamic inferencing are necessary for reflexive reasoning - a kind of inferencing and reasoning that occurs rapidly, spontaneously, and without conscious effort, and which seems necessary for everyday tasks such as natural language understanding. As S&A describe, reflexive reasoning requires a solution to thedynamic binding problem, that is, how to encode systematic and abstract knowledge and instantiate it in specific situations to draw appropriate inferences. Although symbolic artificial (...) intelligence systems trivially solve the dynamic binding problem using computers' registers and pointers, it has remained a difficult problem for connectionist systems. S&A's temporal synchrony solution to the dynamic binding problem using synchronous firing of argument units and the entities that are bound to them illustrates one way in which connectionist networks can do thisusing a constrained but important class of long-term knowledge rules. Their structured connectionist solution allows dynamic inferencing to proceed in parallel and therefore has a number of advantages for reflexive reasoning over most other connectionist and symbolic systems. (shrink)

have context-sensitive constituents, but rather because they sometimes have no constituents at all. The argument to be rejected depends on the assumption that one can only assign propositional contents to representations if one starts by assigning sub-propositional contents to atomic representations. I give some philosophical arguments and present a counterexample to show that this assumption is mistaken.

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)

Some argue the common practice of inferring multiple processes or systems from a dissociation is flawed. One proposed solution is state-trace analysis, which involves plotting, across two or more conditions of interest, performance measured by either two dependent variables, or two conditions of the same dependent measure. The resulting analysis is considered to provide evidence that either a single process underlies performance or there is evidence for more than one process. This article reports simulations using the simple recurrent network (...) in which changes to the learning rate produced state-trace plots with multiple functions. We also report simulations using a single-layer error-correcting network that generate plots with a single function. We argue that the presence of different functions on a state-trace plot does not necessarily support a dual-system account, at least as typically defined ; it can also indicate variation in a single parameter within theories generally considered to be single-system accounts. (shrink)

Two additional sources of evidence are provided in support of localist coding within connectionist networks. First, only models with localist codes can currently represent multiple pieces of information simultaneously or represent order among a set of items on-line. Second, recent priming data appear problematic for theories that rely on distributed representations. However, a faulty argument advanced by Page is also pointed out.

This paper examines whether a classical model could be translated into a PDP network using a standard connectionist training technique called extra output learning. In Study 1, standard machine learning techniques were used to create a decision tree that could be used to classify 8124 different mushrooms as being edible or poisonous on the basis of 21 different Features (Schlimmer, 1987). In Study 2, extra output learning was used to insert this decision tree into a PDP network (...) being trained on the identical problem. An interpretation of the trained network revealed a perfect mapping from its internal structure to the decision tree, representing a precise translation of the classical theory to the connectionist model. In Study 3, a second network was trained on the mushroom problem without using extra output learning. An interpretation of this second network revealed a different algorithm for solving the mushroom problem, demonstrating that the Study 2 network was indeed a proper theory translation. (shrink)

In this paper I defend the propriety of explaining the behavior of distributed connectionist networks by appeal to selected data stored therein. In particular, I argue that if there is a problem with such explanations, it is a consequence of the fact that information storage in networks is superpositional, and not because it is distributed. I then develop a ``proto-account'''' of causation for networks, based on an account of Andy Clark''s, that shows even superpositionality does not undermine information-based explanation. (...) Finally, I argue that the resulting explanations are genuinely informative and not vacuous. (shrink)

Nothing seems more possible to me than that people some day will come to the definite opinion that there is no copy in the… nervous system which corresponds to a particular thought, or a particular idea, or, memory.WittgensteinIn a recent essay it was emphasized that brain and mind appear to the mind as complementary and reciprocally recursive domains of a hermeneutic circle (Fischer, 1987). An outstanding and not yet recognized feature of this hermeneutic circle is that interpretation within this circle (...) is not rule-governed and hence appears self-organized: individual features of the world (or the brain) become intelligible in terms of the whole context (of the mind)… while the entire context becomes intelligible through individual features (or brain functions). How, or from where then is significance arising? (shrink)

Connectionism and the Mind provides a clear and balanced introduction to connectionist networks and explores theoretical and philosophical implications. Much of this discussion from the first edition has been updated, and three new chapters have been added on the relation of connectionism to recent work on dynamical systems theory, artificial life, and cognitive neuroscience. Read two of the sample chapters on line: Connectionism and the Dynamical Approach to Cognition: http://www.blackwellpublishing.com/pdf/bechtel.pdf Networks, Robots, and Artificial Life: http://www.blackwellpublishing.com/pdf/bechtel2.pdf.

The apparent very close similarity between the learning of the past tense by Adam and the Plunkett and Marchman model is exaggerated by several misleading comparisons--including arbitrary, unexplained changes in how graphs were plotted. The model's development differs from Adam's in three important ways: Children show a U-shaped sequence of development which does not depend on abrupt changes in input; U-shaped development in the simulation occurs only after an abrupt change in training regimen. Children overregularize vowel-change verbs more than no-change (...) verbs; the simulation overregularizes vowel-change verbs less often than no-change verbs. Children, including Adam, overregularize more than they irregularize; the simulation overregularized less than it irregularized. Interestingly, the RM model--widely criticized as being inadequate--does somewhat better, correctly overregularizing vowel-change verbs more often than no-change verbs, and overregularizing more often than it irregularizes. Although Plunkett and Marchman's (1993) state of the art model incorporated hidden layers and back-propagation, used a more realistic phonological coding scheme, and explored a broader range of parameters than Rumelhart and McClelland's model, their results are farther from psychological reality. It is unknown whether any connectionist model can mimic a child's performance without resorting to unrealistic exogenous changes in the training or input, but it is clear that adding a hidden-layer and back-propagation does not ensure a solution. (shrink)

Exploratory analysis is an area of increasing interest in the computational linguistics arena. Pragmatically speaking, exploratory analysis may be paraphrased as natural language processing by means of analyzing large corpora of text. Concerning the analysis, appropriate means are statistics, on the one hand, and artificial neural networks, on the other hand. As a challenging application area for exploratory analysis of text corpora we may certainly identify text databases, be it information retrieval or information filtering systems. With this paper we present (...) recent findings of exploratory analysis based on both statistical and neural models applied to legal text corpora. Concerning the artificial neural networks, we rely on a model adhering to the unsupervised learning paradigm. This choice appears naturally when taking into account the specific properties of large text corpora where one is faced with the fact that input-output-mappings as required by supervised learning models cannot be provided beforehand to a satisfying extent. This is due to the fact of the highly changing contents of text archives. In a nutshell, artificial neural networks count for their highly robust behavior regarding the parameters for model optimization. In particular, we found statistical classification techniques much more susceptible to minor parameter variations than unsupervised artificial neural networks. In this paper we describe two different lines of research in exploratory analysis. First, we use the classification methods for concept analysis. The general goal is to uncover different meanings of one and the same natural language concept. A task that, obviously, is of specific importance during the creation of thesauri. As a convenient environment to present the results we selected the legal term of neutrality, which is a perfect representative of a concept having a number of highly divergent meanings. Second, we describe the classification methods in the setting of document classification. The ultimate goal in such an application is to uncover semantic similarities of various text documents in order to increase the efficiency of an information retrieval system. In this sense, document classification has its fixed position in information retrieval research from the very beginning. Nowadays renewed massive interest in document classification may be witnessed due to the appearance of large-scale digital libraries. (shrink)

This paper examines Alvin Goldman's discussion of acceptance and uncertainty in chapter 15 of his book, Epistemology and Cognition. Goldman discusses how acceptance and rejection of beliefs might be understood in terms of "winner-take-all" connectionist networks. The paper answers some of the questions he raises in his epistemic evaluation of connectionist programs. The major tool for doing this is a connectionist model of explanatory coherence judgments (Thagard, Behavioral and Brain Sciences, 1989). Finally, there is a discussion of (...) problems for Goldman's general epistemological project that arise if one adopts a different approach to connectionism based on distributed representations. (shrink)

Connectionism—also known as parallel distributed processing, or neural network modeling—offers promise as a framework to unite clinical and cognitive psychology, and as a tool for studying conscious and unconscious mental activity. This paper describes a neural network model of the case study of Lucy R., from Freud and Breuer's Studies on Hysteria. Though very simple in architecture, the network spontaneously displays analogues of repression and hallucination, corresponding to Lucy R.'s symptoms. Salient elements of Lucy's conscious experience are (...) represented in the model by the activations of neuronlike processors in a fully interconnected network, without hidden units. The model learns to associate elements of experience that were associated in Lucy's case history. Some of these configurations of elements were traumatic for Lucy; trauma is modeled in the network by "emphatic learning," learning accomplished at an abnormally high learning rate. The model suggests that changing associations among conscious elements are sufficient to generate the symptoms Freud observed: apparent repression, hallucination, and recovery through therapy. In the case of Lucy R., Freud's theoretical inference regarding active but unconscious thought is not required by his data. Instead, the unconscious can be understood as a set of complex dispositions embodied in connections between elements of conscious experience. (shrink)

Intended to introduce readers to the use of artificial neural networks in the study of music, this volume contains numerous case studies and research findings that address problems related to identifying scales, keys, classifying musical chords, and learning jazz chord progressions. A detailed analysis of networks is provided for each case study which together demonstrate that focusing on the internal structure of trained networks could yield important contributions to the field of music cognition.

Reviews the contribution of neural network models in psychiatry and psychopathology, including diagnosis, pharmacotherapy and psychotherapy.

Human cognition is said to be systematic: cognitive ability generalizes to structurally related behaviours. The connectionist approach to cognitive theorizing has been strongly criticized for its failure to explain systematicity. Demonstrations of generalization notwithstanding, I show that two widely used networks (feedforward and recurrent) do not support systematicity under the condition of local input/output representations. For a connectionist explanation of systematicity, these results leave two choices, either: (1) develop models capable of systematicity under local input/output representations; or (2) (...) justify the choice of similarity-based (nonlocal) component representations sufficient for systematicity. (shrink)

In this paper, I define tacit knowledge as a kind of causal-explanatory structure, mirroring the derivational structure in the theory that is tacitly known. On this definition, tacit knowledge does not have to be explicitly represented. I then take the notion of a modular theory, and project the idea of modularity to several different levels of description: in particular, to the processing level and the neurophysiological level. The fundamental description of a connectionist network lies at a level between (...) the processing level and the physiological level. At this level, connectionism involves a characteristic departure from modularity, and a correlative absence of syntactic structure. This is linked to the fact that tacit knowledge descriptions of networks are only approximately true. A consequence is that strict causal systematicity in cognitive processes poses a problem for the connectionist programme. (shrink)

Something remarkable is happening in the cognitive sciences. After a quarter of a century of cognitive models that were inspired by the metaphor of the digital computer, the newest cognitive models are inspired by the properties of the brain itself. Variously referred to as connectionist, parallel distributed processing, or neutral network models, they explore the idea that complex intellectual operations can be carried out by large networks of simple, neuron-like units. The units themselves are identical, very low-level and (...) 'stupid'. Intelligent performance is derived from the pattern of connection strengths between units, and the fundamental cognitive activity is pattern recognition and completion. Connectionism and the Mind provides an introduction to this newly emerging approach to understanding the mind. The first few chapters focus on network architecture, offering accessible treatment of the equations that describe learning and the propagation of activation. Furthermore, the reader is walked step-by-step through the activities of networks engaged in pattern recognition, learning, and cognitive tasks such as memory retrieval and prototype formation. The remainder of the book addresses the implications of connectionism for theories of the mind, both philosophical and psychological. Foe example: What Role is played by pattern recognition and completion as basic as cognitive functions? Connectionist models have particular strength in learning and pattern recognition; should they be limited to those functions, or can they provide an overall account of cognitive functioning? In particular, can connectionist models provide an adequate account of the ability to employ linguistic and other symbol systems, or must an adequate system incorporate symbol processing as a basic cognitive capacity? Finally, Connectionism and the Mind examines the relation of connectionist models to philosophical accounts of propositional attitudes, and to a variety of other inquiries in cognitive psychology, linguistics, developmental psychology, artificial intelligence and neuroscience. (shrink)

Connectionist networks have been used to model a wide range of cognitivephenomena, including developmental, neuropsychological and normal adultbehaviours. They have offered radical alternatives to traditional accounts ofwell-established facts about cognition. The primary source of the success ofthese models is their sensitivity to statistical regularities in their trainingenvironment. This paper provides a brief description of the connectionisttoolbox and how this has developed over the past 2 decades, with particularreference to the problem of reading aloud.

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)

Suri and Gross's 2022 connectionist emotion theory can be considered as one version of a family of theories known as network theories of emotion. It presents similarities and differences with older...

When cognitive scientists apply computational theory to the problem of phenomenal consciousness, as many of them have been doing recently, there are two fundamentally distinct approaches available. Either consciousness is to be explained in terms of the nature of the representational vehicles the brain deploys; or it is to be explained in terms of the computational processes defined over these vehicles. We call versions of these two approaches _vehicle_ and _process_ theories of consciousness, respectively. However, while there may be space (...) for vehicle theories of consciousness in cognitive science, they are relatively rare. This is because of the influence exerted, on the one hand, by a large body of research which purports to show that the explicit representation of information in the brain and conscious experience are _dissociable_, and on the other, by the _classical_ computational theory of mind – the theory that takes human cognition to be a species of symbol manipulation. But two recent developments in cognitive science combine to suggest that a reappraisal of this situation is in order. First, a number of theorists have recently been highly critical of the experimental methodologies employed in the dissociation studies – so critical, in fact, it’s no longer reasonable to assume that the dissociability of conscious experience and explicit representation has been adequately demonstrated. Second, classicism, as a theory of human cognition, is no longer as dominant in cognitive science as it once was. It now has a lively competitor in the form of _connectionism; _and connectionism, unlike classicism, does have the computational resources to support a robust vehicle theory of consciousness. In this paper we develop and defend this connectionist vehicle theory of consciousness. It takes the form of the following simple empirical hypothesis: _phenomenal experience consists in the explicit_ _representation of information in neurally realized PDP networks_.. (shrink)

This paper reviews four significant advances on the feedforward architecture that has dominated discussions of connectionism. The first involves introducing modularity into networks by employing procedures whereby different networks learn to perform different components of a task, and a Gating Network determines which network is best equiped to respond to a given input. The second consists in the use of recurrent inputs whereby information from a previous cycle of processing is made available on later cycles. The third development (...) involves developing compressed representations of strings in which there is no longer an explicit encoding of the components but where information about the structure of the original string can be recovered and so is present functionally. The final advance entails using connectionist learning procedures not just to change weights in networks but to change the patterns used as inputs to the network. These advances significantly increase the usefulness of connectionist networks for modeling human cognitive performance by, among other things, providing tools for explaining the productivity and systematicity of some mental activities, and developing representations that are sensitive to the content they are to represent. (shrink)

This paper has a two-fold aim. First, it reinforces a version of the "syntactic argument" given in Aizawa (1994). This argument shows that connectionist networks do not provide a means of implementing representations without rules. Horgan and Tlenson have responded to the syntactic argument in their book and in another paper (Horgan & Tlenson, 1993), but their responses do not meet the challenge posed by my formulation of the syntactic argument. My second aim is to describe a kind of (...) cognitive architecture. This architecture might be called a computational architecture, but it is not a rules and representations architecture nor the representations without rules architecture that Horgan and Tlenson wish to endorse. (shrink)

Connectionism seems to avoid many of the problems of classical artificial intelligence, but has it avoided all of them? In this thesis I examine the problem that Intentionality, the directedness of thought to an object, raises for connectionism. As a preliminary approach, I consider the role of Intentionality in classical artificial intelligence from the programmer’s point of view. In this investigation, one problem I identify with classical artificial intelligence is that the Intentionality of the programmer seems to be projected onto (...) the system, rather than the programmer creating a system whereby Intentionality arises intrinsically within the system. -/- In considering the current practice of connectionism, the same problem with Intentionality reappears. The assignment of Intentional content to input or output nodes in a neural network likewise projects the Intentionality of the programmer onto the system, and that projection is often reinforced by the training process of the neural network. However, connectionism seems to have an advantage over classical artificial intelligence in this respect, in that there is a form of neural network in which the network itself organizes the output nodes. The challenge is to utilize these self-organizing networks without having the programmer project Intentionality onto the system in an act of interpretation. -/- I suggest that the way to overcome these problems in connectionism is to embody the neural network within a world, whether physical or virtual, and to allow the system to develop concepts purely empirically. In this manner, connectionism can make scientific observations concerning the nature of cognition without the risk of contamination from the programmer’s own Intentionality. (shrink)

This paper discusses the relation between cognitive and implementational levels of analysis. Chalmers (1990, 1993) argues that a connectionist implementation of a classical cognitive architecture possesses a compositional semantics, and therefore undercuts Fodor and Pylyshyn's (1988) argument that connectionist networks cannot possess a compositional semantics. I argue that Chalmers argument misconstrues the relation between cognitive and implementational levels of analysis. This paper clarifies the distinction, and shows that while Fodor and Pylyshyn's argument survives Chalmers' critique, it cannot be (...) used to establish the irrelevance of neurophysiological implementation to cognitive modeling; some aspects of Chater and Oaksford's (1990) response to Fodor and Pylyshyn, though not all, are therefore cogent. (shrink)

There is widespread belief that connectionist networks are dramatically different from classical or symbolic models. However, connectionists rarely test this belief by interpreting the internal structure of their nets. A new approach to interpreting networks was recently introduced by Berkeley et al. (1995). The current paper examines two implications of applying this method: (1) that the internal structure of a connectionist network can have a very classical appearance, and (2) that this interpretation can provide a cognitive theory (...) that cannot be dismissed as a mere implementation. (shrink)

In Connectionism and the Philosophy of Psychology, Horgan and Tienson (1996) argue that cognitive processes, pace classicism, are not governed by exceptionless, “representation-level” rules; they are instead the work of defeasible cognitive tendencies subserved by the non-linear dynamics of the brain’s neural networks. Many theorists are sympathetic with the dynamical characterisation of connectionism and the general (re)conception of cognition that it affords. But in all the excitement surrounding the connectionist revolution in cognitive science, it has largely gone unnoticed that (...) connectionism adds to the traditional focus on computational processes, a new focus – one on the vehicles of mental representation, on the entities that carry content through the mind. Indeed, if Horgan and Tienson’s dynamical characterisation of connectionism is on the right track, then so intimate is the relationship between computational processes and representational vehicles, that connectionist cognitive science is committed to a resemblance theory of mental content. (shrink)

This is an overview of recent philosophical discussion about connectionism and the foundations of cognitive science. Connectionist modeling in cognitive science is described. Three broad conceptions of the mind are characterized, and their comparative strengths and weaknesses are discussed: (1) the classical computation conception in cognitive science; (2) a popular foundational interpretation of connectionism that John Tienson and I call “non‐sentential computationalism”; and (3) an alternative interpretation of connectionism we call “dynamical cognition.” Also discussed are two recent philosophical attempts (...) to enlist connectionism in defense of eliminativism about folk psychology. (shrink)

At present, the prevailing Connectionist methodology forrepresenting rules is toimplicitly embody rules in neurally-wired networks. That is, the methodology adopts the stance that rules must either be hard-wired or trained into neural structures, rather than represented via explicit symbolic structures. Even recent attempts to implementproduction systems within connectionist networks have assumed that condition-action rules (or rule schema) are to be embodied in thestructure of individual networks. Such networks must be grown or trained over a significant span of time. (...) However, arguments are presented herein that humanssometimes follow rules which arevery rapidly assignedexplicit internal representations, and that humans possessgeneral mechanisms capable of interpreting and following such rules. In particular, arguments are presented that thespeed with which humans are able to follow rules ofnovel structure demonstrates the existence of general-purpose rule following mechanisms. It is further argued that the existence of general-purpose rule following mechanisms strongly indicates that explicit rule following is not anisolated phenomenon, but may well be a common and important aspect of cognition. The relationship of the foregoing conclusions to Smolensky''s view of explicit rule following is also explored. The arguments presented here are pragmatic in nature, and are contrasted with thekind of arguments developed by Fodor and Pylyshyn in their recent, influential paper. (shrink)