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)

When it comes to applying computational theory to the problem of phenomenal consciousness, cognitive scientists appear to face a dilemma. The only strategy that seems to be available is one that explains consciousness in terms of special kinds of computational processes. But such theories, while they dominate the field, have counter-intuitive consequences; in particular, they force one to accept that phenomenal experience is composed of information processing effects. For cognitive scientists, therefore, it seems to come down to a choice between (...) a counter-intuitive theory or no theory at all. We offer a way out of this dilemma. We argue that the computational theory of mind doesn't force cognitive scientists to explain consciousness in terms of computational processes, as there is an alternative strategy available: one that focuses on the representational vehicles that encode information in the brain. This alternative approach to consciousness allows us to do justice to the standard intuitions about phenomenal experience, yet remain within the confines of cognitive science. (shrink)

In recent years, the family of algorithms collected under the term ``deep learning'' has revolutionized artificial intelligence, enabling machines to reach human-like performances in many complex cognitive tasks. Although deep learning models are grounded in the connectionist paradigm, their recent advances were basically developed with engineering goals in mind. Despite of their applied focus, deep learning models eventually seem fruitful for cognitive purposes. This can be thought as a kind of biological exaptation, where a physiological structure becomes applicable for a (...) function different from that for which it was selected. In this paper, it will be argued that it is time for cognitive science to seriously come to terms with deep learning, and we try to spell out the reasons why this is the case. First, the path of the evolution of deep learning from the connectionist project is traced, demonstrating the remarkable continuity, and the differences as well. Then, it will be considered how deep learning models can be useful for many cognitive topics, especially those where it has achieved performance comparable to humans, from perception to language. It will be maintained that deep learning poses questions that cognitive sciences should try to answer. One of such questions is the reasons why deep convolutional models that are disembodied, inactive, unaware of context, and static, are by far the closest to the patterns of activation in the brain visual system. (shrink)

SUMMARY Major theories of philosophical psychology and philosophy of mind are examined on the basis of the fundamental questions of ontology, metaphysics, epistemology, semantics and logic. The result is the choice between language of eliminative reductionism and dualism, neither of which answers properly the relation between mind and body. In the search for a non–dualistic and non–reductive language, Wittgenstein’s notion of language–games as the representative links between language and the world is considered together with Peirce’s semeiosis of cognition. The result (...) is a redefined notion of cognition as the goal–oriented ability to instantiate strategies from the rules of the language–games. Cognition is considered within the four-dimensional languagegames: rules/strategies, primitive/complete language-games, family-resemblances/forms of life, and non-temporal continuum as the language-games’ modality. Cognition is seen as a continuum process of non–individualized elements that unites perception, volition, emotion, will and thought against the commonly accepted understandings of cognition in exclusive terms of perception and thinking. The alternative to the mind/body problem is the continuity of cognition where rules and strategies, syntax and semantics, are considered inseparable within language–games. This continuity of cognition is explained in terms of virtual (univocal) identity, replacing the old philosophical paradigm of the mind/body problem. -/- SOMMARIO Le teorie maggiori della psicologia filosofica e filosofia della mente sono esaminate a partire dalle questioni fondamentali di ontologia, metafisica, epistemologia, semantica e logica. Il risultato è la scelta tra un linguaggio riduzionista eliminativo e un dualismo che però non confronta in modo adeguato la relazione tra mente e corpo. Nella ricerca per un linguaggio non-dualistico e non-riduttivo, viene considerata la nozione del gioco linguistico di Wittgenstein come un legame rappresentativo tra il linguaggio e il mondo insieme con la semiosi cognitiva di Peirce. Il risultato è la nozione ridefinita della cognizione come abilità goal-orientata di creare le strategie dalle regole dei giochi linguistici. La cognizione è considerata entro le quattro dimensioni dei giochi linguistici: regole/strategie, giochi linguistici primitivi/completi, somiglianze di famiglia/forme di vita, e la continuità atemporale come la modalità dei giochi linguistici. La cognizione diventa un processo continuo degli elementi non-individualizzati che tende ad unificare la percezione, volizione, emozione, la volontà e il pensiero contro un concetto generalmente accettato di vedere la cognizione nei termini esclusivamente di percezione e di pensiero. L’alternativa al problema della mente/corpo è la continuità della cognizione, dove le regole e le strategie, la sintassi e la semantica, sono considerate inseparabili nei giochi linguistici. Questa continuità della cognizione è spiegata nei termini dell’identità virtuale (univoca) sostituendo un paradigma filosofico previo del problema della mente/corpo. (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)

Although radical forms of relativism are perhaps beyond the epistemological pale, I argue here that a more moderate form may be plausible, and articulate the conditions under which moderate epistemic relativism could well serve our epistemic goals. In particular, as a result of our limitations as human cognizers, we find ourselves needing to investigate the dappled and difficult world by means of competing communities of highly specialized researchers. We would do well, I argue, to admit of the existence of unresolvable (...) disputes between such communities, but only so long as there is a sufficient amount of fruitful exchange between them as well. I close with some speculation about when it is or is not legitimate to make an “appeal to discipline”: responding to another’s argument by saying something like, “we should do it this way, because we are philosophers (/linguists/psychologists/…), and that’s just what we do”. (shrink)

O'Brien & Opie's (O&O's) theory demands a view of unconscious processing that is incompatible with virtually all current PDP models of neural activity. Relative to the alternatives, the theory is closer to an AI than a parallel distributed processing (PDP) perspective, and its treatment of phenomenology is ad hoc. It raises at least one important question: Could features of network relaxation be the “switch” that turns an unconscious into a conscious network?

Connectionist research first emerged in the 1940s. The first phase of connectionism attracted a certain amount of media attention, but scant philosophical interest. The phase came to an abrupt halt, due to the efforts of Minsky and Papert (1969), when they argued for the intrinsic limitations of the approach. In the mid-1980s connectionism saw a resurgence. This marked the beginning of the second phase of connectionist research. This phase did attract considerable philosophical attention. It was of philosophical interest, as it (...) offered a way of counteracting the conceptual ties to the philosophical traditions of atomism, rationalism, logic, nativism, rule realism and a concern with the role symbols play in human cognitive functioning, which was prevalent as a consequence of artificial intelligence research. The surge in philosophical interest waned, possibly in part due to the efforts of some traditionalists and the so-called black box problem. Most recently, what may be thought of as a third phase of connectionist research, based on so-called deep learning methods, is beginning to show some signs of again exciting philosophical interest. (shrink)

David Marr provided a useful framework for theorizing about cognition within classical, AI-style cognitive science, in terms of three levels of description: the levels of (i) cognitive function, (ii) algorithm and (iii) physical implementation. We generalize this framework: (i) cognitive state transitions, (ii) mathematical/functional design and (iii) physical implementation or realization. Specifying the middle, design level to be the theory of dynamical systems yields a nonclassical, alternative framework that suits (but is not committed to) connectionism. We consider how a brain's (...) (or a network's) being a dynamical system might be the key both to its realizing various essential features of cognition — productivity, systematicity, structure-sensitive processing, syntax — and also to a non-classical solution of (frame-type) problems plaguing classical cognitive science. (shrink)

Fodor and Pylyshyn (1988) argue that any successful model of cognition must use classical architecture; it must depend upon rule-based processing sensitive to constituent structure. This claim is central to their defense of classical AI against the recent enthusiasm for connectionism. Connectionist nets, they contend, may serve as theories of the implementation of cognition, but never as proper theories of psychology. Connectionist models are doomed to describing the brain at the wrong level, leaving the classical view to account for the (...) mind.This paper considers whether recent results in connectionist research weigh against Fodor and Pylyshyn's thesis. The investigation will force us to develop criteria for determining exactly when a net is capable of systematic processing. Fodor and Pylyshyn clearly intend their thesis to affect the course of research in psychology. I will argue that when systematicity is defined in a way that makes the thesis relevant in this way, the thesis is challenged by recent progress in connectionism. (shrink)

Proponents of the language of thought (LOT) thesis are realists when it comes to syntactically structured representations, and must defend their view against instrumentalists, who would claim that syntactic structures may be useful in describing cognition, but have no more causal powers in governing cognition than do the equations of physics in guiding the planets. This paper explores what it will take to provide an argument for LOT that can defend its conclusion from instrumentalism. I illustrate a difficulty in this (...) project by discussing arguments for LOT put forward by Horgan and Tienson. When their evidence is viewed in the light of results in connectionist research, it is hard to see how a realist conception of syntax can be formulated and defended. (shrink)

One of the principal tasks Dennett sets himself in Consciousness Explained is to demolish the Cartesian theater model of phenomenal consciousness, which in its contemporary garb takes the form of Cartesian materialism: the idea that conscious experience is a process of presentation realized in the physical materials of the brain. The now standard response to Dennett is that, in focusing on Cartesian materialism, he attacks an impossibly naive account of consciousness held by no one currently working in cognitive science or (...) the philosophy of mind. Our response is quite different. We believe that, once properly formulated, Cartesian materialism is no straw man. Rather, it is an attractive hypothesis about the relationship between the computational architecture of the brain and phenomenal consciousness, and hence one that is worthy of further exploration. Consequently, our primary aim in this paper is to defend Cartesian materialism from Dennett’s assault. We do this by showing that Dennett’s argument against this position is founded on an implicit assumption (about the relationship between phenomenal experience and information coding in the brain), which while valid in the context of classical cognitive science, is not forced on connectionism. (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)

Classical computational modellers of mind urge that the mind is something like a von Neumann computer operating over a system of symbols constituting a language of thought. Such an architecture, they argue, presents us with the best explanation of the compositionality, systematicity and productivity of thought. The language of thought hypothesis is supported by additional independent arguments made popular by Jerry Fodor. Paul Smolensky has developed a connectionist architecture he claims adequately explains compositionality, systematicity and productivity without positing any language (...) of thought, and without positing any operations over a set of symbols. This architecture encodes the information represented in linguistic trees without explicitly representing those trees or their constituents, and indeed without employing any representational vehicles with constituent structure. In a recent article, Fodor (1997; Connectionism and systematicity, Cognition , 62, 109-119) argues that Smolensky's proposal does not work. I defend Smolensky against Fodor's attack, and use this interchange as a vehicle for exploring and criticising the “Language of Thought” hypothesis more generally and the arguments Fodor adduces on its behalf. (shrink)

David Marr provided an influential account of levels of description in classical cognitive science. In this paper we contrast Marr'ent with some alternatives that are suggested by the recent emergence of connectionism. Marr's account is interesting and important both because of the levels of description it distinguishes, and because of the way his presentation reflects some of the most basic, foundational, assumptions of classical AI-style cognitive science . Thus, by focusing on levels of description, one can sharpen foundational differences between (...) classicism and potential non-classical conceptions of mentality that might emerge under the rubric of connectionism. (shrink)

This paper explores a line of argument against the classical paradigm in cognitive science that is based upon properties of non-linear dynamical systems, especially in their chaotic and near-chaotic behavior. Systems of this kind are capable of generating information-rich macro behavior that could be useful to cognition. I argue that a brain operating at the edge of chaos could generate high-complexity cognition in this way. If this hypothesis is correct, then the symbolic processing methodology in cognitive science faces serious obstacles. (...) A symbolic description of the mind will be extremely difficult, and even if it is achieved to some approximation, there will still be reasons for rejecting the hypothesis that the brain is in fact a symbolic processor. (shrink)

David Marr provided an influential account of levels of description in classical cognitive science. In this paper we contrast Marr'ent with some alternatives that are suggested by the recent emergence of connectionism. Marr's account is interesting and important both because of the levels of description it distinguishes, and because of the way his presentation reflects some of the most basic, foundational, assumptions of classical AI-style cognitive science. Thus, by focusing on levels of description, one can sharpen foundational differences between classicism (...) and potential non-classical conceptions of mentality that might emerge under the rubric of connectionism. (shrink)

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)

The computational theory of cognition (CTC) holds that the mind is akin to computer software. This article aims to show that CTC is incorrect because it is not able to distinguish the ability to solve a maze from the ability to solve its mirror image. CTC cannot do so because it only individuates brain states up to isomorphism. It is shown that a finer individuation that would distinguish left-handed from right-handed abilities is not compatible with CTC. The view is explored (...) that CTC correctly individuates in an autonomous domain of the mental, leaving discrimination between left and right to some non-cognitive component of psychology such as physiology. I object by showing that the individuation provided by CTC does not properly describe in any domain. An embodied computational taxonomy, rather than software alone, is required for an adequate science of the mind. (shrink)

O'Brien & Opie do not address the question of the psychotherapeutic role of unconscious representational states such as beliefs. A dilemma is proposed: if they accept the legitimacy of such states then they should modify what they say about dissociation, and if they do not, they owe us an account of why.

The argument I present here is an example of the manner in which naturalizing epistemology can help address fairly traditional epistemological issues. I develop one argument against coherentist epistemologies of empirical knowledge. In doing so, I draw on BonJour (1985), for that account seems to me to indicate the direction in which any plausible coherentist account would need to be developed, at least insofar as such accounts are to conceive of justification in terms of an agent (minimally) possessing articul able (...) reasons and arguments, as is standard. I end by indicating important elements of coherentist epistemology that can be salvaged in the face of my argument, provided we are willing to drop the traditional commitment to characterizing justification in terms of the structure of articulable argument. (shrink)

To begin, I introduce an analysis of interlevel relations that allows us to offer an initial characterization of the debate about the way classical and connectionist models relate. Subsequently, I examine a compatibility thesis and a conditional claim on this issue.With respect to the compatibility thesis, I argue that, even if classical and connectionist models are not necessarily incompatible, the emergence of the latter seems to undermine the best arguments for the Language of Thought Hypothesis, which is essential to the (...) former. (shrink)