The aim of this paper is to demonstrate a _prima facie_ tension between our commonsense conception of ourselves as thinkers and the connectionist programme for modelling cognitive processes. The language of thought hypothesis plays a pivotal role. The connectionist paradigm is opposed to the language of thought; and there is an argument for the language of thought that draws on features of the commonsense scheme of thoughts, concepts, and inference. Most of the paper (Sections 3-7) is taken up with the (...) argument for the language of thought hypothesis. The argument for an opposition between connectionism and the language of thought comes towards the end (Section 8), along with some discussion of the potential eliminativist consequences (Sections 9 and. (shrink)
This paper offers both a theoretical and an experimental perspective on the relationship between connectionist and Classical (symbol-processing) models. Firstly, a serious flaw in Fodor and Pylyshyn’s argument against connectionism is pointed out: if, in fact, a part of their argument is valid, then it establishes a conclusion quite different from that which they intend, a conclusion which is demonstrably false. The source of this flaw is traced to an underestimation of the differences between localist and distributed representation. It (...) has been claimed that distributed representations cannot support systematic operations, or that if they can, then they will be mere implementations of traditional ideas. This paper presents experimental evidence against this conclusion: distributed representations can be used to support direct structure-sensitive operations, in a man- ner quite unlike the Classical approach. Finally, it is argued that even if Fodor and Pylyshyn’s argument that connectionist models of compositionality must be mere implementations were correct, then this would still not be a serious argument against connectionism as a theory of mind. (shrink)
Fodor and Pylyshyn (1988) have argued that the cognitive architecture is not Connectionist. Their argument takes the following form: (1) the cognitive architecture is Classical; (2) Classicalism and Connectionism are incompatible; (3) therefore the cognitive architecture is not Connectionist. In this essay I argue that Fodor and Pylyshyn's defenses of (1) and (2) are inadequate. Their argument for (1), based on their claim that Classicalism best explains the systematicity of cognitive capacities, is an invalid instance of inference to the (...) best explanation. And their argument for (2) turns out to be question-begging. The upshot is that, while Fodor and Pylyshyn have presented Connectionists with the important empirical challenge of explaining systematicity, they have failed to provide sufficient reason for inferring that the cognitive architecture is Classical and not Connectionist. (shrink)
Fodor and Pylyshyn's critique of connectionism has posed a challenge to connectionists: Adequately explain such nomological regularities as systematicity and productivity without postulating a "language of thought" (LOT). Some connectionists like Smolensky took the challenge very seriously, and attempted to meet it by developing models that were supposed to be non-classical. At the core of these attempts lies the claim that connectionist models can provide a representational system with a combinatorial syntax and processes sensitive to syntactic structure. They are (...) not implementation models because, it is claimed, the way they obtain syntax and structure sensitivity is not "concatenative," hence "radically different" from the way classicists handle them. In this paper, I offer an analysis of what it is to physically satisfy/realize a formal system. In this context, I examine the minimal truth-conditions of LOT Hypothesis. From my analysis it will follow that concatenative realization of formal systems is irrelevant to LOTH since the very notion of LOT is indifferent to such an implementation level issue as concatenation. I will conclude that to the extent to which they can explain the law-like cognitive regularities, a certain class of connectionist models proposed as radical alternatives to the classical LOT paradigm will in fact turn out to be LOT models, even though new and potentially very exciting ones. (shrink)
Recently some philosophers have urged that connectionist artificial intelligence is (potentially) eliminative for the propositional attitudes of folk psychology. At the same time, however, these philosophers have also insisted that since philosophy of science has failed to provide criteria distinguishing ontologically retentive from eliminative theory changes, the resulting eliminativism is not principled. Application of some resources developed within the semantic view of scientific theories, particularly recent formal work on the theory reduction relation, reveals these philosophers to be wrong in this (...) second contention, yet by and large correct in the first. (shrink)
In an influential critique, Jerry Fodor and Zenon Pylyshyn point to the existence of a potentially devastating dilemma for connectionism (Fodor and Pylyshyn [1988]). Either connectionist models consist in mere associations of unstructured representations, or they consist in processes involving complex representations. If the former, connectionism is mere associationism, and will not be capable of accounting for very much of cognition. If the latter, then connectionist models concern only the implementation of cognitive processes, and are, therefore, not informative (...) at the level of cognition. I shall argue that Fodor and Pylyshyn's argument is based on a crucial misunderstanding, the same misunderstanding which motivates the entire language of thought hypothesis. (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)
Terry Horgan and John Tienson have suggested that connectionism might provide a framework within which to articulate a theory of cognition according to which there are mental representations without rules (RWR) (Horgan and Tienson 1988, 1989, 1991, 1992). In essence, RWR states that cognition involves representations in a language of thought, but that these representations are not manipulated by the sort of rules that have traditionally been posited. In the development of RWR, Horgan and Tienson attempt to forestall a (...) particular line of criticism, theSyntactic Argument, which would show RWR to be inconsistent with connectionism. In essence, the argument claims that the node-level rules of connectionist networks, along with the semantic interpretations assigned to patterns of activation, serve to determine a set of representation-level rules incompatible with the RWR conception of cognition. The present paper argues that the Syntactic Argument can be made to show that RWR is inconsistent with connectionism. (shrink)
The relation between logic and thought has long been controversial, but has recently influenced theorizing about the nature of mental processes in cognitive science. One prominent tradition argues that to explain the systematicity of thought we must posit syntactically structured representations inside the cognitive system which can be operated upon by structure sensitive rules similar to those employed in systems of natural deduction. I have argued elsewhere that the systematicity of human thought might better be explained as resulting from the (...) fact that we have learned natural languages which are themselves syntactically structured. According to this view, symbols of natural language are external to the cognitive processing system and what the cognitive system must learn to do is produce and comprehend such symbols. In this paper I pursue that idea by arguing that ability in natural deduction itself may rely on pattern recognition abilities that enable us to operate on external symbols rather than encodings of rules that might be applied to internal representations. To support this suggestion, I present a series of experiments with connectionist networks that have been trained to construct simple natural deductions in sentential logic. These networks not only succeed in reconstructing the derivations on which they have been trained, but in constructing new derivations that are only similar to the ones on which they have been trained. (shrink)
Much of the philosophical interest of cognitive science stems from its potential relevance to the mind/body problem. The mind/body problem concerns whether both mental and physical phenomena exist, and if so, whether they are distinct. In this chapter I want to portray the classical and connectionist frameworks in cognitive science as potential sources of evidence for or against a particular strategy for solving the mind/body problem. It is not my aim to offer a full assessment of these two frameworks in (...) this capacity. Instead, in this thesis I will deal with three philosophical issues which are (at best) preliminaries to such an assessment: issues about the syntax, the semantics, and the processing of the mental representations countenanced by classical and connectionist models. I will characterize these three issues in more detail at the end of the chapter. (shrink)
This paper investigates connectionism's potential to solve the frame problem. The frame problem arises in the context of modelling the human ability to see the relevant consequences of events in a situation. It has been claimed to be unsolvable for classical cognitive science, but easily manageable for connectionism. We will focus on a representational approach to the frame problem which advocates the use of intrinsic representations. We argue that although connectionism's distributed representations may look promising from this (...) perspective, doubts can be raised about the potential of distributed representations to allow large amounts of complexly structured information to be adequately encoded and processed. It is questionable whether connectionist models that are claimed to effectively represent structured information can be scaled up to a realistic extent. We conclude that the frame problem provides a difficulty to connectionism that is no less serious than the obstacle it constitutes for classical cognitive science. (shrink)
Along with the increasing popularity of connectionist language models has come a number of provocative suggestions about the challenge these models present to Chomsky's arguments for nativism. The aim of this paper is to assess these claims. We begin by reconstructing Chomsky's argument from the poverty of the stimulus and arguing that it is best understood as three related arguments, with increasingly strong conclusions. Next, we provide a brief introduction to connectionism and give a quick survey of recent efforts (...) to develop networks that model various aspects of human linguistic behavior. Finally, we explore the implications of this research for Chomsky's arguments. Our claim is that the relation between connectionism and Chomsky's views on innate knowledge is more complicated than many have assumed, and that even if these models enjoy considerable success the threat they pose for linguistic nativism is small. (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)
Abstract Ramsey, Stick and Garon (1991) argue that if the correct theory of mind is some parallel distributed processing theory, then folk psychology must be false. Their idea is that if the nodes and connections that encode one representation are causally active then all representations encoded by the same set of nodes and connections are also causally active. We present a clear, and concrete, counterexample to RSG's argument. In conclusion, we suggest that folk psychology and connectionism are best understood (...) as complementary theories. Each has different limitations, yet each will co?evolve with the other in an overlapping domain of ?normal? psychology. (shrink)
In this paper I critically examine the line of reasoning that has recently appeared in the literature that connects connectionism with eliminativism. This line of reasoning has it that if connectionist models turn out accurately to characterize our cognition, then beliefs, desires and the other intentional entities of commonsense psychology will be eliminated from our theoretical ontology. In complete contrast I argue (1) that not only is this line of reasoning mistaken about the eliminativist tendencies of connectionist models, but (...) (2) that these models have the potential to provide a more robust vindication of commonsense psychology than classical computational models. (shrink)
The philosophy of cognitive science has recently become one of the most exciting and fastest growing domains of philosophical inquiry and analysis. Until the early 1980s, nearly all of the models developed treated cognitive processes -- like problem solving, language comprehension, memory, and higher visual processing -- as rule-governed symbol manipulation. However, this situation has changed dramatically over the last half dozen years. In that period there has been an enormous shift of attention toward connectionist models of cognition that are (...) inspired by the network-like architecture of the brain. Because of their unique architecture and style of processing, connectionist systems are generally regarded as radically different from the more traditional symbol manipulation models. This collection was designed to provide philosophers who have been working in the area of cognitive science with a forum for expressing their views on these recent developments. Because the symbol-manipulating paradigm has been so important to the work of contemporary philosophers, many have watched the emergence of connectionism with considerable interest. The contributors take very different stands toward connectionism, but all agree that the potential exists for a radical shift in the way many philosophers think of various aspects of cognition. Exploring this potential and other philosophical dimensions of connectionist research is the aim of this volume. (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.
Antireductionist philosophers have argued for higher-order classifications of qualia that locate consciousness outside the scope of conventional scientific explanations, viz., by classifying qualia as intrinsic, basic, or subjective properties, antireductionists distinguish qualia from extrinsic, complex, and objective properties, and thereby distinguish conscious mental states from the possible explananda of functionalist or physicalist explanations. I argue that, in important respects, qualia are intrinsic, basic, and subjective properties of conscious mental states, and that, contrary to antireductionists' suggestions, these (...) higher-order classifications are compatible with qualia reduction. I demonstrate this compatibility by examining the putative higher-order properties of qualia and comparing them to the higher-order properties characteristic of connectionist models of cognitive processes. I contend that the higher-order properties characteristic of connectionist networks approximate (in intertheoretic terms) the putative higher-order properties of qualia sufficiently well to conclude that qualia reductionism can (1) accommodate claims that qualia are intrinsic, basic, and subjective properties, and (2) explain the motivating intuitions for those claims generated by inverted, absent, and alien qualia thought experiments. In this way I argue that (approximate versions of) the putative higher-order classifications of qualia not only fail to defeat qualia reduction but, ironically, turn out to support it. (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)
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 brains 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 Tiensons 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)
Philosophy and Memory Traces defends two theories of autobiographical memory. One is a bewildering historical view of memories as dynamic patterns in fleeting animal spirits, nervous fluids which rummaged through the pores of brain and body. The other is new connectionism, in which memories are 'stored' only superpositionally, and reconstructed rather than reproduced. Both models, argues John Sutton, depart from static archival metaphors by employing distributed representation, which brings interference and confusion between memory traces. Both raise urgent issues about (...) control of the personal past, and about relations between self and body. Sutton demonstrates the role of bizarre body fluids in moral physiology, as philosophers from Descartes and Locke to Coleridge struggled to control their own innards and impose cognitive discipline on 'the phantasmal chaos of association'. Going on to defend connectionism against Fodor and critics of passive mental representations, he shows how problems of the self are implicated in cognitive science. (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)
Connectionism provides hope for unifying work in neuroscience, computer science, and cognitive psychology. This promise has met with some resistance from Classical Computionalists, which may have inspired Connectionists to retaliate with bold, inflationary claims on behalf of Connectionist models. This paper demonstrates, by examining three intimately connected issues, that these inflationary claims made on behalf of Connectionism are wrong. This should not be construed as an attack on Connectionism, however, since the inflated claims made on its behalf (...) have the look of cures for which there are no ailments. There is nothing wrong with Connectionism for its failure to solve illusory problems. (shrink)
Simulation has emerged as an increasingly popular account of folk psychological (FP) talents at mind-reading: predicting and explaining human mental states. Where its rival (the theory-theory) postulates that these abilities are explained by mastery of laws describing the connections between beliefs, desires, and action, simulation theory proposes that we mind-read by "putting ourselves in another's shoes." This paper concerns connectionist architecture and the debate between simulation theory (ST) and the theory-theory (TT). It is only natural to associate TT with classical (...) architectures where rule governed operations apply to explicit propositional representations. On the other hand, ST would seem better tuned to procedurally oriented non-symbolic structures found in connectionist models. This paper explores the possible alignment between ST and connectionist architecture. Joe Cruz argues that connectionist models with distributed non-symbolic representations are particularly well suited to simulation theory. The purported linkage between connectionist architecture and simulation theory is criticized in this paper. The conclusion is that there are reasons for thinking that connectionist forms of representation are the enemy of both TT and ST. So the contribution of connectionism may be to suggest the need for an alternative to both views. (shrink)
A competence model describes the abstract structure of a solution to some problem. or class of problems, facing the would-be intelligent system. Competence models can be quite derailed, specifying far more than merely the function to be computed. But for all that, they are pitched at some level of abstraction from the details of any particular algorithm or processing strategy which may be said to realize the competence. Indeed, it is the point and virtue of such models to specify some (...) equivalence class of algorithms/processing strategies so that the common properties highlighted by the chosen class may feature in psychologically interesting accounts. A question arises concerning the type of relation a theorist might expect to hold between such a competence model and a psychologically real processing strategy. Classical work in cognitive science expects the actual processing to depend on explicit or tacit knowledge of the competence theory. Connectionist work, for reasons to be explained, represents a departure from this norm. But the precise way in which a connectionist approach may disturb the satisfying classical symmetry of competence and processing has yet to be properly specified. A standard ?Newtonian? connectionist account, due to Paul Smolensky, is discussed and contrasted with a somewhat different ?rogue? account. A standard connectionist understanding has it that a classical competence theory describes an idealized subset of a network's behaviour. But the network's behaviour is not to be explained by its embodying explicit or tacit knowledge of the information laid out in the competence theory. A rogue model, by contrast, posits either two systems, or two aspects of a single system, such that one system does indeed embody the knowledge laid out in the competence theory. (shrink)
In "Representations without Rules, Connectionism and the Syntactic Argument'', Kenneth Aizawa argues against the view that connectionist nets can be understood as processing representations without the use of representation-level rules, and he provides a positive characterization of how to interpret connectionist nets as following representation-level rules. He takes Terry Horgan and John Tienson to be the targets of his critique. The present paper marshals functional and methodological considerations, gleaned from the practice of cognitive modelling, to argue against Aizawa's characterization (...) of how connectionist nets may be understood as making use of representation-level rules. (shrink)
Any analysis of the concept of computation as it occurs in the context of a discussion of the computational model of the mind must be consonant with the philosophic burden traditionally carried by that concept as providing a bridge between a physical and a psychological description of an agent. With this analysis in hand, one may ask the question: are connectionist-based systems consistent with the computational model of the mind? The answer depends upon which of several versions of connectionism (...) one presupposes: non-learning connectionist-based systems as simulated on digital computers are consistent with the computational model of the mind, whereas connectionist-based systems (/dynamical systems) qua analog systems are not. (shrink)
This paper presents considerations in favour of the view that traditional (classical) architectures can be seen as emergent features of connectionist networks with distributed representation. A recent paper by William Bechtel (1988) which argues for a similar conclusion is unsatisfactory in that it fails to consider whether the compositional syntax and semantics attributed to mental representations by classical models can emerge within a connectionist network. The compatibility of the two paradigms hinges largely, I suggest, on how this question is answered. (...) Focusing on the issue of syntax, I argue that while such structure is lacking in connectionist models with local representation, it can be accommodated within networks where representation is distributed. I discuss an important paper by Smolenski (1988) which attempts to show how connectionists can incorporate the relevant syntactic structure, suggesting that some criticisms levelled against that paper by Fodor & Pylyshyn (1988) are wanting. I then go on to indicate a strategy by which a compositional syntax and semantics can be defined for the sort of network that Smolenski describes. I conclude that since the connectionist can respect the central tenets of classicism, the two approaches are compatible with one another. (shrink)
Recent experimental findings reveal dissociations of conscious and nonconscious performance in many fields of psychological research, suggesting that conscious and nonconscious effects result from qualitatively different processes. A connectionist view of these processes is put forward in which consciousness is the consequence of construction processes taking place in three types of working memory in a specific type of recurrent neural network. The recurrences arise by feeding back output to the input of a central (representational) network. They are assumed to be (...) intemalizations of motor-sensory feedback through the environment. In this manner, a subvocal-phonological, a visuo-spatial, and a somatosensory working memory may have developed. Representations in the central network, which constitutes long-term memory, can be kept active by rehearsal in the feedback loops. The sequentially recurrent architecture allows for recursive symbolic operations and the formation of (auditory, visual, or somatic) models of the external world which can be maintained, transformed and temporarily combined with other information in working memory. Moreover, the quasi-input from the loop directs subsequent attentional processing. The view may contribute to a formal framework to accommodate findings from disparate fields such as working memory, sequential reasoning, and conscious and nonconscious processes in memory and emotion. In theory, but probably not very soon in practice, such connectionist models might simulate aspects of consciousness. (shrink)
It is widely assumed that common sense psychological explanations of human action are a species of causal explanation. I argue against this construal, drawing on Ramsey et al.'s paper, “Connectionism, eliminativism, and the future of folk psychology”. I argue that if certain connec-tionist models are correct, then mental states cannot be identified with functionally discrete causes of behavior, and I respond to some recent attempts to deny this claim. However, I further contend that our common sense psychological practices are (...) not committed to the falsity of such connectionist models. The paper concludes that common sense psychology is not committed to the identification of mental states with functionally discrete causes of behavior, and hence that common sense psychology is not committed to the causal account of action explanation. (shrink)
The introduction of connectionist or parallel distributed processing (PDP) systems to model cognitive functions has raised the question of the possible relations between these models and traditional information processing models which employ rules to manipulate representations. After presenting a brief account of PDP models and two ways in which they are commonly interpreted by those seeking to use them to explain cognitive functions, I present two ways one might relate these models to traditional information processing models and so not totally (...) repudiate the tradition of modelling cognition through systems of rules and representations. The proposal that seems most promising is that PDP-type structures might provide the underlying framework in which a rule and representation model might be implemented. To show how one might pursue such a strategy, I discuss recent research by Barsalou on the instability of concepts and show how that might be accounted for in a system whose microstructure had a PDP architecture. I also outline how adopting a multi-leveled view of the mind, where on one level the mind employed a PDP-type system and at another level constituted a rule processing system, would allow researchers to relocate some problems which seemed difficult to explain at one level, such as the capacity for concept learning, to another level where it could be handled in a straightforward manner. (shrink)
It is not widely realised that Turing was probably the first person to consider building computing machines out of simple, neuron-like elements connected together into networks in a largely random manner. Turing called his networks unorganised machines. By the application of what he described as appropriate interference, mimicking education an unorganised machine can be trained to perform any task that a Turing machine can carry out, provided the number of neurons is sufficient. Turing proposed simulating both the behaviour of the (...) network and the training process by means of a computer program. We outline Turing's connectionist project of 1948. (shrink)
Marinov''s critique I argue, is vitiated by its failure to recognize the distinctive role of superposition within the distributed connectionist paradigm. The use of so-called subsymbolic distributed encodings alone is not, I agree, enough to justify treating distributed connectionism as a distinctive approach. It has always been clear that microfeatural decomposition is both possible and actual within the confines of recognizably classical approaches. When such approaches also involve statistically-driven learning algorithms — as in the case of ID3 — the (...) fundamental differences become even harder to spot. To see them, it is necessary to consider not just the nature of an acquired input-output function but the nature of the representational scheme underlying it. Differences between such schemes make themselves best felt outside the domain of immediate problem solving. It is in the more extended contexts of performance DURING learning and cognitive change as a result of SUBSEQUENT training on new tasks (or simultaneous training on several tasks) that the effects of superpositional storage techniques come to the fore. I conclude that subsymbols, distribution and statistically driven learning alone are indeed not of the essence. But connectionism is not just about subsymbols and distribution. It is about the generation of whole subsymbol SYSTEMS in which multiple distributed representations are created and superposed. (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)
Fodor's and Pylyshyn's stand on systematicity in thought and language has been debated and criticized. Van Gelder and Niklasson, among others, have argued that Fodor and Pylyshyn offer no precise definition of systematicity. However, our concern here is with a learning based formulation of that concept. In particular, Hadley has proposed that a network exhibits strong semantic systematicity when, as a result of training, it can assign appropriate meaning representations to novel sentences (both simple and embedded) which contain words in (...) syntactic positions they did not occupy during training. The experience of researchers indicates that strong systematicity in any form is difficult to achieve in connectionist systems.Herein we describe a network which displays strong semantic systematicity in response to Hebbian, connectionist training. During training, two-thirds of all nouns are presented only in a single syntactic position (either as grammatical subject or object). Yet, during testing, the network correctly interprets thousands of sentences containing those nouns in novel positions. In addition, the network generalizes to novel levels of embedding. Successful training requires a, corpus of about 1000 sentences, and network training is quite rapid. The architecture and learning algorithms are purely connectionist, but classical insights are discernible in one respect, viz, that complex semantic representations spatially contain their semantic constituents. However, in other important respects, the architecture is distinctly non-classical. (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)
A possible relation between Derrida's deconstruction of metaphysics and connectionism is explored by considering diff rance in neural nets terms. First diff rance , as the crossing of Saussurian difference and Freudian deferral, is modeled and then the fuller 'sheaf of diff rance is taken up. The metaphysically conceived brain has two versions: in the traditional computational version the brain processes information like a computer and in the connectionist version the brain computes input vector to output vector transformations non-symbolically. (...) The 'deconstructed brain' neither processes information nor computes functions but is spontaneously economical. (shrink)
I sketch a theory of cognitive representation from recent "connectionist" cognitive science. I then argue that (i) this theory is reducible to neuroscientific theories, yet (ii) its kinds are multiply realized at a neurobiological level. This argument demonstrates that multiple realizability alone is no barrier to the reducibility of psychological theories. I conclude that the multiple realizability argument, the most influential argument against psychophysical reductionism, should be abandoned.
One new tradition that has emerged from early research on autonomous robots is embodied cognitive science. This paper describes the relationship between embodied cognitive science and a related tradition, synthetic psychology. It is argued that while both are synthetic, embodied cognitive science is antirepresentational while synthetic psychology still appeals to representations. It is further argued that modern connectionism offers a medium for conducting synthetic psychology, provided that researchers analyze the internal representations that their networks develop. The paper then provides (...) a detailed example of the synthetic approach by showing how the construction (and subsequent analysis) of a connectionist network can be used to contribute to a theory of how humans solve Piaget's classic balance scale task. (shrink)
In the late 1980s, there were many who heralded the emergence of connectionism as a new paradigm – one which would eventually displace the classically symbolic methods then dominant in AI and Cognitive Science. At present, there remain influential connectionists who continue to defend connectionism as a more realistic paradigm for modeling cognition, at all levels of abstraction, than the classical methods of AI. Not infrequently, one encounters arguments along these lines: given what we know about neurophysiology, it (...) is just not plausible to suppose that our brains are digital computers. Thus, they could not support a classical architecture. I argue here for a middle ground between connectionism and classicism. I assume, for argument's sake, that some form(s) of connectionism can provide reasonably approximate models – at least for lower-level cognitive processes. Given this assumption, I argue on theoretical and empirical grounds that most human mental skills must reside in separate connectionist modules or sub-networks. Ultimately, it is argued that the basic tenets of connectionism, in conjunction with the fact that humans often employ novel combinations of skill modules in rule following and problem solving, lead to the plausible conclusion that, in certain domains, high level cognition requires some form of classical architecture. During the course of argument, it emerges that only an architecture with classical structure could support the novel patterns of information flow and interaction that would exist among the relevant set of modules. Such a classical architecture might very well reside in the abstract levels of a hybrid system whose lower-level modules are purely connectionist. (shrink)
For the past three decades linguistic theory has been based on the assumption that sentences are interpreted and constructed by the brain by means of computational processes analogous to those of a serial-digital computer. The recent interest in devices based on the neural network or parallel distributed processor (PDP) principle raises the possibility ("eliminative connectionism") that such devices may ultimately replace the S-D computer as the model for the interpretation and generation of language by the brain. An analysis of (...) the differences between the two models suggests that the effect of such a development would be to steer linguistic theory towards a return to the empiricism and behaviorism which prevailed before it was driven by Chomsky towards nativism and mentalism. Linguists, however, will not be persuaded to return to such a theory unless and until it can deal with the phenomenon of novel sentence construction as effectively as its nativist/mentalist rival. (shrink)
Uses connectionism (neural networks) to extract the "gist" of a story in order to represent a context going forward for the disambiguation of incoming words as a text is processed.
There is much in The Sensory Order that recommends the oft-made claim that Hayek anticipated connectionist theories of mind. To the extent that this is so, contemporary arguments against and for connectionism, as advanced by Jerry Fodor, Zenon Pylyshyn, and John Searle, are shown as applicable to theoretical psychology. However, the final section of this chapter highlights an important disanalogy between theoretical psychology and connectionist theories of mind.
This paper explores how an evolutionary process can produce systems that learn. A general framework for the evolution of learning is outlined, and is applied to the task of evolving mechanisms suitable for supervised learning in single-layer neural networks. Dynamic properties of a network’s information-processing capacity are encoded genetically, and these properties are subjected to selective pressure based on their success in producing adaptive behavior in diverse environments. As a result of selection and genetic recombination, various successful learning mechanisms evolve, (...) including the well-known delta rule. The effect of environmental diversity on the evolution of learning is investigated, and the role of different kinds of emergent phenomena in genetic and connectionist systems is discussed. (shrink)
We think the best prospect for a naturalistic explanation of phenomenal consciousness is to be found at the confluence of two influential ideas about the mind. The first is the _computational _ _theory of mind_: the theory that treats human cognitive processes as disciplined operations over neurally realised representing vehicles.1 The second is the _representationalist theory of _ _consciousness_: the theory that takes the phenomenal character of conscious experiences (the “what-it-is-likeness”) to be constituted by their representational content.2 Together these two (...) theories suggest that phenomenal consciousness might be explicable in terms of the representational content of the neurally realised representing vehicles that are generated and manipulated in the course of cognition. The simplest and most elegant hypothesis that one might entertain in this regard is that conscious experiences are identical to (i.e., are one and the same as) the brain’s representing vehicles. (shrink)
Figure 1: A pr ototyp ical exa mple of a three-layer feed forward network, used by Plunkett and M archm an (1 991 ) to simulate learning the past-tense of En glish verbs. The inpu t units encode representations of the three phonemes of the present tense of the artificial words used in this simulation. Th e netwo rk is trained to produce a representation of the phonemes employed in the past tense form and the suffix (/d/, /ed/, or /t/) (...) used on regular verbs. To run the network, each input unit is assigned an activation value o f 0 or 1 , dep ending on whethe r the featu re is present or not. Eac h input unit is conne cted to each of the 30 hidden units by a we ighted conn ection and p rovid es an inp ut to each hidden unit equal to the product of the input unit's activation and the weight. Each hidd en unit's activation is then determined by summing ov er the va lues co ming fro m each inp ut unit to deter mine a netinput, and then applying a non-linear function (e.g., the logistic function 1/(1+enetinput). Th is whole proced ure is. (shrink)
The paper considers the problems involved in getting neural networks to learn about highly structured task domains. A central problem concerns the tendency of networks to learn only a set of shallow (non-generalizable) representations for the task, i.e., to miss the deep organizing features of the domain. Various solutions are examined, including task specific network configuration and incremental learning. The latter strategy is the more attractive, since it holds out the promise of a task-independent solution to the problem. Once we (...) see exactly how the solution works, however, it becomes clear that it is limited to a special class of cases in which (1) statistically driven undersampling is (luckily) equivalent to task decomposition, and (2) the dangers of unlearning are somehow being minimized. The technique is suggestive nonetheless, for a variety of developmental factors may yield the functional equivalent of both statistical AND informed undersampling in early learning. (shrink)
