The notion of Simulative Reasoning in the study of propositional attitudes within Artificial Intelligence (AI) is strongly related to the Simulation Theory of mental ascription in Philosophy. Roughly speaking, when an AI system engages in Simulative Reasoning about a target agent, it reasons with that agent’s beliefs as temporary hypotheses of its own, thereby coming to conclusions about what the agent might conclude or might have concluded. The contrast is with non-simulative meta-reasoning, where the AI system reasons within a detailed (...) theory about the agent’s (conjectured) reasoning acts. The motive within AI for preferring Simulative Reasoning is that it is more convenient and efficient, because of a simplification of the representations and reasoning processes. The chapter discusses this advantage in detail. It also sketches the use of Simulative Reasoning in an AI natural language processing system, ATT-Meta, that is currently being implemented. This system is directed at the understanding of propositional attitude reports. In ATT-Meta, Simulative Reasoning is yoked to a somewhat independent set of ideas about how attitude reports should be treated. Central here are the claims that (a) speakers often employ commonsense (and largely metaphorical) models of mind in describing agents’ attitudes, (b) the listener accordingly needs often to reason within the terms of such models, rather than on the basis of any objectively justifiable characterization of the mind, and (c) the commonsense models filter the suggestions that Simulative Reasoning comes up with concerning target agents’ reasoning conclusions. There is a yet tighter connection between the commonsense models and the Simulative Reasoning. It turns out that Simulative Reasoning can be rationally reconstructed in terms of a more general type of reasoning about the possibly-counterfactual “world” that the target agent believes in, together with an assumption that that agent has a faithful representation of the world. In the ATT-Meta approach, the reasoner adopts that assumption when it views the target agent through a particular commonsense model (called IDEAS-AS-MODELS). (shrink)

If Australasian philosophers constitute the kind of group to which a collective identity or broadly shared self-image can plausibly be ascribed, the celebrated history of Australian materialism rightly lies close to its heart. Jack Smart’s chapter in this volume, along with an outstanding series of briefer essays in A Companion to Philosophy in Australia and New Zealand (Forrest 2010; Gold 2010; Koksvik 2010; Lycan 2010; Matthews 2010; Nagasawa 2010; Opie 2010; Stoljar 2010a), effectively describe the naturalistic realism of Australian philosophy (...) of mind. In occasional semi-serious psychogeographic speculation, this long-standing and strongly-felt intellectual attitude has been traced back to the influences of our light, land, or lifestyle (Devitt 1996, x; compare comments by Chalmers and O’Brien in Mitchell, 2006). Australasian work in philosophy of mind and cognition has become more diverse in the last 40 years, but is almost all still marked, in one way or another, by the history of these debates on materialism. (shrink)

Over the past thirty years, it is been common to hear the mind likened to a digital computer. This essay is concerned with a particular philosophical view that holds that the mind literally is a digital computer (in a specific sense of “computer” to be developed), and that thought literally is a kind of computation. This view—which will be called the “Computational Theory of Mind” (CTM)—is thus to be distinguished from other and broader attempts to connect the mind with computation, (...) including (a) various enterprises at modeling features of the mind using computational modeling techniques, and (b) employing some feature or features of production-model computers (such as the stored program concept, or the distinction between hardware and software) merely as a guiding metaphor for understanding some feature of the mind. This entry is therefore concerned solely with the Computational Theory of Mind (CTM) proposed by Hilary Putnam [1961] and developed most notably for philosophers by Jerry Fodor [1975, 1980, 1987, 1993]. The senses of ‘computer’ and ‘computation’ employed here are technical; the main tasks of this entry will therefore be to elucidate: (a) the technical sense of ‘computation’ that is at issue, (b) the ways in which it is claimed to be applicable to the mind, (c) the philosophical problems this understanding of the mind is claimed to solve, and (d) the major criticisms that have accrued to this view. (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)

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)

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)

A comprehensive introduction to the Language of Though Hypothesis (LOTH) accessible to general audiences. LOTH is an empirical thesis about thought and thinking. For their explication, it postulates a physically realized system of representations that have a combinatorial syntax (and semantics) such that operations on representations are causally sensitive only to the syntactic properties of representations. According to LOTH, thought is, roughly, the tokening of a representation that has a syntactic (constituent) structure with an appropriate semantics. Thinking thus consists in (...) syntactic operations defined over representations. Most of the arguments for LOTH derive their strength from their ability to explain certain empirical phenomena like productivity, systematicity of thought and thinking. (shrink)

I argue that analogue mental representations possess a canonical decomposition into privileged constituents from which they compose. I motivate this suggestion, and rebut arguments to the contrary, through reflection on the approximate number system, whose representations are widely expected to have an analogue format. I then argue that arguments for the compositionality and constituent structure of these analogue representations generalize to other analogue mental representations posited in the human mind, such as those in early vision and visual imagery.

This paper aims to offer a new view of the role of connectionist models in the study of human cognition through the conceptualization of the history of connectionism – from the simplest perceptrons to convolutional neural nets based on deep learning techniques, as well as through the interpretation of criticism coming from symbolic cognitive science. Namely, the connectionist approach in cognitive science was the target of sharp criticism from the symbolists, which on several occasions caused its marginalization and almost complete (...) abandonment of its assumptions in the study of cognition. Criticisms have mostly pointed to its explanatory inadequacy as a theory of cognition or to its biological implausibility as a theory of implementation, and critics often focused on specific shortcomings of some connectionist models and argued that they apply to connectionism in general. In this paper, we want to show that both types of critique are based on the assumption that the only valid explanations in cognitive science are instances of homuncular functionalism and that by removing this assumption and by adopting an alternative methodology – exploratory mechanistic strategy, we can reject most objections to connectionism as irrelevant, explain the progress of connectionist models despite their shortcomings and sketch the trajectory of their future development. By adopting mechanistic explanations and by criticizing functionalism, we will reject the objections of explanatory inadequacy, by characterizing connectionist models as generic rather than concrete mechanisms, we will reject the objections of biological implausibility, and by attributing the exploratory character to connectionist models we will show that practice of generalizing current to general failures of connectionism is unjustified. (shrink)

This paper explores early Australasian philosophy in some detail. Two approaches have dominated Western philosophy in Australia: idealism and materialism. Idealism was prevalent between the 1880s and the 1930s, but dissipated thereafter. Idealism in Australia often reflected Kantian themes, but it also reflected the revival of interest in Hegel through the work of ‘absolute idealists’ such as T. H. Green, F. H. Bradley, and Henry Jones. A number of the early New Zealand philosophers were also educated in the idealist tradition (...) and were influential in their communities, but produced relatively little. In Australia, materialism gained prominence through the work of John Anderson, who arrived in Australia in 1927, and continues to be influential. John Anderson had been a student of Henry Jones, who might therefore be said to have influenced both main strands of Australian philosophical thought. (shrink)

The Humean view that conceivability entails possibility can be criticized via input from cognitive psychology. A mainstream view here has it that there are two candidate codings for mental representations (one of them being, according to some, reducible to the other): the linguistic and the pictorial, the difference between the two consisting in the degree of arbitrariness of the representation relation. If the conceivability of P at issue for Humeans involves the having of a linguistic mental representation, then it is (...) easy to show that we can conceive the impossible, for impossibilities can be represented by meaningful bits of language. If the conceivability of P amounts to the pictorial imaginability of a situation verifying P, then the question is whether the imagination at issue works purely qualitatively, that is, only by phenomenological resemblance with the imagined scenario. If so, the range of situations imaginable in this way is too limited to have a significant role in modal epistemology. If not, imagination will involve some arbitrary labeling component, which turns out to be sufficient for imagining the impossible. And if the relevant imagination is neither linguistic nor pictorial, Humeans will appear to resort to some representational magic, until they come up with a theory of a ‘third code’ for mental representations. (shrink)

Naturally occurring speech contains only a limited amount of complex recursive structure, and this is reflected in the empirically documented difficulties that people experience when processing such structures. We present a connectionist model of human performance in processing recursive language structures. The model is trained on simple artificial languages. We find that the qualitative performance profile of the model matches human behavior, both on the relative difficulty of center‐embedding and cross‐dependency, and between the processing of these complex recursive structures and (...) right‐branching recursive constructions. We analyze how these differences in performance are reflected in the internal representations of the model by performing discriminant analyses on these representations both before and after training. Furthermore, we show how a network trained to process recursive structures can also generate such structures in a probabilistic fashion. This work suggests a novel explanation of people's limited recursive performance, without assuming the existence of a mentally represented competence grammar allowing unbounded recursion. (shrink)

Connectionist attention to variables has been too restricted in two ways. First, it has not exploited certain ways of doing without variables in the symbolic arena. One variable-avoidance method, that of logical combinators, is particularly well established there. Secondly, the attention has been largely restricted to variables in long-term rules embodied in connection weight patterns. However, short-lived bodies of information, such as sentence interpretations or inference products, may involve quantification. Therefore short-lived activation patterns may need to achieve the effect of (...) variables. The paper is mainly a theoretical analysis of some benefits and drawbacks of using logical combinators to avoid variables in short-lived connectionist encodings without loss of expressive power. The paper also includes a brief survey of some possible methods for avoiding variables other than by using combinators. (shrink)

In 1988 Fodor and Pylyshyn issued a challenge to the newly-popular connectionism: explain the systematicity of cognition without merely implementing a so-called classical architecture. Since that time quite a number of connectionist models have been put forward, either by their designers or by others, as in some measure demonstrating that the challenge can be met (e.g., Pollack, 1988, 1990; Smolensky, 1990; Chalmers, 1990; Niklasson and Sharkey, 1992; Brousse, 1993). Unfortu- nately, it has generally been unclear whether these models actually do (...) have this implication (see, for instance, the extensive philosophical debate in Smolensky, 1988; Fodor and McLaughlin, 1990; van Gelder, 1990, 1991; McLaughlin, 1993a, 1993b; Clark, 1993). Indeed, we know of no major supporter of classical orthodoxy who has felt compelled, by connectionist models and argu- ments, to concede in print that connectionists have in fact delivered a non-classical explanation of systematicity. (shrink)

More than a decade ago, philosopher John Searle started a long-running controversy with his paper “Minds, Brains, and Programs” (Searle, 1980a), an attack on the ambitious claims of artificial intelligence (AI). With his now famous _Chinese Room_ argument, Searle claimed to show that despite the best efforts of AI researchers, a computer could never recreate such vital properties of human mentality as intentionality, subjectivity, and understanding. The AI research program is based on the underlying assumption that all important aspects of (...) human cognition may in principle be captured in a computational model. This assumption stems from the belief that beyond a certain level, implementational details are irrelevant to cognition. According to this belief, neurons, and biological wetware in general, have no preferred status as the substrate for a mind. As it happens, the best examples of minds we have at present have arisen from a carbon-based substrate, but this is due to constraints of evolution and possibly historical accidents, rather than to an absolute metaphysical necessity. As a result of this belief, many cognitive scientists have chosen to focus not on the biological substrate of the mind, but instead on the abstract causal structure_ _that the mind embodies (at an appropriate level of abstraction). The view that it is abstract causal structure that is essential to mentality has been an implicit assumption of the AI research program since Turing (1950), but was first articulated explicitly, in various forms, by Putnam (1960), Armstrong (1970) and Lewis (1970), and has become known as _functionalism_. From here, it is a very short step to _computationalism_, the view that computational structure is what is important in capturing the essence of mentality. This step follows from a belief that any abstract causal structure can be captured computationally: a belief made plausible by the Church–Turing Thesis, which articulates the power. (shrink)

A distributed neural network model called SPEC for processing sentences with recursive relative clauses is described. The model is based on separating the tasks of segmenting the input word sequence into clauses, forming the case‐role representations, and keeping track of the recursive embeddings into different modules. The system needs to be trained only with the basic sentence constructs, and it generalizes not only to new instances of familiar relative clause structures but to novel structures as well. SPEC exhibits plausible memory (...) degradation as the depth of the center embeddings increases, its memory is primed by earlier constituents, and its performance is aided by semantic constraints between the constituents. The ability to process structure is largely due to a central executive network that monitors and controls the execution of the entire system. This way, in contrast to earlier subsymbolic systems, parsing is modeled as a controlled high‐level process rather than one based on automatic reflex responses. (shrink)

The proponents of embodied cognition often try to present their research program as the next step in the evolution of standard cognitive science. The domain of standard cognitive science is fairly clearly circumscribed (perception, memory, attention, language, problem solving, learning). Its ontological commitments, that is, its commitments to various theoretical entities, are overt: cognition involves algorithmic processes upon symbolic representations. As a research program, embodied cognition exhibits much greater latitude in subject matter, ontological commitment, and methodology than does standard cognitive (...) science. The proponents of embodied cognition to explain the aspects of human cognition are using the importance of embodied interaction with the environment, which is a dynamic relation. The cause of disagreement between these two approaches is regarding the role assumed by the notion of representation. The discussion about the contrast between embodied cognition and standard cognitive science is incomplete without Gibson’s ecological theory of perception and connectionist account of cognition. I will briefly contrast these important theories with computational view of cognition, highlighting the debate over role of representation. Embodied cognition has incorporated rather extensively a variety of insights emerging from research both in ecological psychology and in connectionism. The way I have followed to contrast embodied cognition with standard cognitive science, involves concentration on those several themes that appear to be prominent in the body of work that is often seen as illustrative of embodied cognition. This strategy has the advantage of postponing hard questions about “the” subject matter, ontological commitments, and methods of embodied cognition until more is understood about the particular interests and goals that embodied cognition theorists often pursue. This approach might show embodied cognition to be poorly unified, suggesting that the embodied cognition label should be abandoned in favor of several labels that reflect more accurately the distinct projects that have been clumped together under a single title. Alternatively, it might show that, in fact, there are some overarching commitments that bring tighter unity to the various bodies of work within embodied cognition that seem thematically only loosely related. The contrast between these two approaches is highlighted not only the basis of a priori argument but major experiments have been mentioned, to show the weight of the assumptions of both the contrasting approaches. (shrink)

Performance on the Wason selection task varies with content. This has been taken to demonstrate that there are different cognitive modules for dealing with different conceptual domains. This implication is only legitimate if our underlying cognitive architecture is formal. A non-formal system can explain content-sensitive inference without appeal to independent inferential modules.

We address the problem of musical variation (identification of different musical sequences as variations) and its implications for mental representations of music. According to reductionist theories, listeners judge the structural importance of musical events while forming mental representations. These judgments may result from the production of reduced memory representations that retain only the musical gist. In a study of improvised music performance, pianists produced variations on melodies. Analyses of the musical events retained across variations provided support for the reductionist account (...) of structural importance. A neural network trained to produce reduced memory representations for the same melodies represented structurally important events more efficiently than others. Agreement among the musicians' improvisations, the network model, and music‐theoretic predictions suggest that perceived constancy across musical variation is a natural result of a reductionist mechanism for producing memory representations. (shrink)

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)

This paper deals with the problem of understanding semiosis and meaning in cognitive systems. To this aim we argue for a unified two-factor account according to which both external and internal information are non-independent aspects of meaning, thus contributing as a whole in determining its nature. To overcome the difficulties stemming from this approach we put forward a theoretical scheme based on the definition of a suitable representation space endowed with a set of transformations, and we show how it can (...) be implemented, in the case of a single agent, by a neural network architecture. Numerical experiments conducted on different instances of the latter show that similar representations are developed as a consequence of the fact that these instances are facing a similar semantic task. This allows to model social and environmental influences through a system of interacting agents, each described by a specific implementation of this model architecture. (shrink)

This paper addresses the question of whether mental representations are compositional. Several researchers have claimed recently that there are empirical data that show mental representations to be context-sensitive in a way that threatens compositionality. Some have then gone on to claim that connectionist encoding schemes are well suited to accommodate such noncom-positionality. I argue here that the data do not show that mental representations are noncompositional, and that there are significant problems with the suggested interpretations of connectionist encoding schemes.

Despite the considerable attention that the systematicity argument has enjoyed, it is worthwhile examining the argument within the context of similar explanatory arguments from the history of science. This kind of analysis helps show that Connectionism, qua Connectionism, really does not have an explanation of systematicity. Second, and more surprisingly, one finds that the systematicity argument sets such a high explanatory standard that not even Classicism can explain the systematicity of thought.

Despite its strengths, Leech et al.'s model fails to address the important benefits that derive from self-explanation and task feedback in analogical reasoning development. These components encourage explicit, self-reflective processes that do not necessarily link to knowledge accretion. We wonder, therefore, what mechanisms can be included within a connectionist framework to model self-reflective involvement and its beneficial consequences.

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)

Classicists and connectionists alike claim to be able to explain systematicity. The proposed classicist explanation, I argue, is little more than a promissory note, one that classicists have no idea how to redeem. Smolensky's (1995) proposed connectionist explanation fares little better: it is not vulnerable to recent classicist objections, but it nonetheless fails, particularly if one requires, as some classicists do, that explanations of systematicity take the form of a‘functional analysis’. Nonetheless, there are, I argue, reasons for cautious optimism about (...) the prospects of a connectionist explanation. (shrink)

Leech et al.'s model proposes representing relations as primed transformations rather than as structured representations (explicit representations of relations and their roles dynamically bound to fillers). However, this renders the model unable to explain several developmental trends (including relational integration and all changes not attributable to growth in relational knowledge). We suggest looking to an alternative computational model that learns structured representations from examples.

One of the main challenges that Jerry Fodor and Zenon Pylyshyn (Cognition 28:3–71, 1988) posed for any connectionist theory of cognitive architecture is to explain the systematicity of thought without implementing a Language of Thought (LOT) architecture. The systematicity challenge presents a dilemma: if connectionism cannot explain the systematicity of thought, then it fails to offer an adequate theory of cognitive architecture; and if it explains the systematicity of thought by implementing a LOT architecture, then it fails to offer an (...) alternative to the LOT hypothesis. Given that thought is systematic, connectionism can offer an adequate alternative to the LOT hypothesis only if it can meet the challenge. Although some critics tried to meet the challenge, others argued that it need not be met since thought is not in fact systematic; and some claimed not to even understand the claim that thought is systematic. I do not here examine attempts to answer the challenge. Instead, I defend the challenge itself by explicating the notion of systematicity in a way that I hope makes clear that thought is indeed systematic, and so that to offer an adequate alternative to the LOT hypothesis, connectionism must meet the challenge. (shrink)

Multiple explanatory frameworks may be required to provide an adequate account of human cognition. This paper embeds the classical account within a neural network framework, exploring the encoding of syntacticallystructured objects over the synchronicdiachronic characteristics of networks. Synchronic structure is defined in terms of temporal binding and the superposition of states. To accommodate asymmetric relations, synchronic structure is subject to the type uniqueness constraint. The nature of synchronic structure is shown to underlie Xbar theory that characterizes the phrasal structure of (...) human languages. The derivation differentiates core Xbar properties from languagespecific properties. (shrink)