Representation in Connectionism

This selective review explores biologically inspired learning as a model for intelligent robot control and sensing technology on the basis of specific examples. Hebbian synaptic learning is discussed as a functionally relevant model for machine learning and intelligence, as explained on the basis of examples from the highly plastic biological neural networks of invertebrates and vertebrates. Its potential for adaptive learning and control without supervision, the generation of functional complexity, and control architectures based on self-organization is brought forward. Learning without (...) prior knowledge based on excitatory and inhibitory neural mechanisms accounts for the process through which survival-relevant or task-relevant representations are either reinforced or suppressed. The basic mechanisms of unsupervised biological learning drive synaptic plasticity and adaptation for behavioral success in living brains with different levels of complexity. The insights collected here point toward the Hebbian model as a choice solution for “intelligent” robotics and sensor systems. Keywords: Hebbian learning; synaptic plasticity; neural networks; self-organization; brain; reinforcement; sensory processing; robot control . (shrink)

Neuroclassicism is the view that cognition is explained by “classical” computing mechanisms in the nervous system that exhibit a clear demarcation between processing machinery and read–write memory. The psychologist C. R. Gallistel has mounted a sophisticated defense of neuroclassicism by drawing from ethology and computability theory to argue that animal brains necessarily contain read–write memory mechanisms. This argument threatens to undermine the “connectionist” orthodoxy in contemporary neuroscience, which does not seem to recognize any such mechanisms. In this paper I argue (...) that the neuroclassicist critique rests on a misunderstanding of how computability theory constrains theorizing about natural computing mechanisms. (shrink)

The standard approach to model how human beings understand natural languages is the symbolic, compositional approach according to which the meaning of a complex expression is a function of the meanings of its constituents. In other words, meaning plays a fundamental role in the model. In this work, because of the polysemous, flexible, dynamic, and contextual structure of natural languages, this approach is rejected. Instead, a connectionist model which eliminates the concept of meaning is proposed.

Symmetry in biological and physical systems is a product of self-organization driven by evolutionary processes, or mechanical systems under constraints. Symmetry-based feature extraction or representation by neural networks may unravel the most informative contents in large image databases. Despite significant achievements of artificial intelligence in recognition and classification of regular patterns, the problem of uncertainty remains a major challenge in ambiguous data. In this study, we present an artificial neural network that detects symmetry uncertainty states in human observers. To this (...) end, we exploit a neural network metric in the output of a biologically inspired Self- Organizing Map Quantization Error (SOM-QE). Shape pairs with perfect geometry mirror symmetry but a non-homogenous appearance, caused by local variations in hue, saturation, or lightness within and/or across the shapes in a given pair produce, as shown here, a longer choice response time (RT) for “yes” responses relative to symmetry. These data are consistently mirrored by the variations in the SOM-QE from unsupervised neural network analysis of the same stimulus images. The neural network metric is thus capable of detecting and scaling human symmetry uncertainty in response to patterns. Such capacity is tightly linked to the metric’s proven selectivity to local contrast and color variations in large and highly complex image data. (shrink)

Many philosophers claim that the neurocomputational framework of predictive processing entails a globally inferentialist and representationalist view of cognition. Here, I contend that this is not correct. I argue that, given the theoretical commitments these philosophers endorse, no structure within predictive processing systems can be rightfully identified as a representational vehicle. To do so, I first examine some of the theoretical commitments these philosophers share, and show that these commitments provide a set of necessary conditions the satisfaction of which allows (...) us to identify representational vehicles. Having done so, I introduce a predictive processing system capable of active inference, in the form of a simple robotic “brain”. I examine it thoroughly, and show that, given the necessary conditions highlighted above, none of its components qualifies as a representational vehicle. I then consider and allay some worries my claim could raise. I consider whether the anti-representationalist verdict thus obtained could be generalized, and provide some reasons favoring a positive answer. I further consider whether my arguments here could be blocked by allowing the same representational vehicle to possess multiple contents, and whether my arguments entail some extreme form of revisionism, answering in the negative in both cases. A quick conclusion follows. (shrink)

The quantization error in a fixed-size Self-Organizing Map (SOM) with unsupervised winner-take-all learning has previously been used successfully to detect, in minimal computation time, highly meaningful changes across images in medical time series and in time series of satellite images. Here, the functional properties of the quantization error in SOM are explored further to show that the metric is capable of reliably discriminating between the finest differences in local contrast intensities and contrast signs. While this capability of the QE is (...) akin to functional characteristics of a specific class of retinal ganglion cells (the so-called Y-cells) in the visual systems of the primate and the cat, the sensitivity of the QE surpasses the capacity limits of human visual detection. Here, the quantization error in the SOM is found to reliably signal changes in contrast or colour when contrast information is removed from or added to the image, but not when the amount and relative weight of contrast information is constant and only the local spatial position of contrast elements in the pattern changes. While the RGB Mean reflects coarser changes in colour or contrast well enough, the SOM-QE is shown to outperform the RGB Mean in the detection of single-pixel changes in images with up to five million pixels. This could have important implications in the context of unsupervised image learning and computational building block approaches to large sets of image data (big data). (shrink)

In recent years, a number of different disciplines have begun to investigate the fundamental role context appears to play in a number of cognitive phenomena. Traditionally, linguistics, and the fields of communication and pragmatics in particular, have been the areas that have focused the most on contextual effects. Context has increasingly been studied for its role in influencing mental concepts, for some scholars being considered constitutive for most – if not all – concepts. Cognitive neuroscience is now starting to consider (...) in a systematic way how context interacts with neural responses, although this research is still scattered and concentrated in a small number of specific cases only. In this chapter, we attempt to tie these three levels together, since only from their integration can a comprehensive explanation of how context affects cognition be constructed. The way context drives language comprehension depends on the effects of context on the conceptual scaffolding of the listener, which in turn, is the result of his neural responses in combination to context. These neural responses derive from learning throughout the history of experiences of the individual, and the association between possible contexts and heard utterances. The road we take to accomplishing the multi-level integration between what appear to be distant domains, is a computational one. This approach meets with the mechanistic framework of explanation, which is currently held as the most appropriate way of approaching cognitive phenomena that is often characterized by a multiplicity of levels, as is the case with context. The core underlying concept of the neurocomputational framework here proposed, is an account of neural representation, based on structural similarity. Structural representations are still the best option on the market in cognitive science, but in their traditional form, derived from classical measurement theory, are affected by a number of serious drawbacks, including not being able to account for context. We suggest a different account of structural similarity, one informed by current neuroscience, where the homomorphic relations required for structural similarity are derived from neural population coding. In a preliminary mathematical sketch, we indicate how this approach can construct neural aggegations that are sensitive to context. (shrink)

In this paper, we consider how certain longstanding philosophical questions about mental representation may be answered on the assumption that cognitive and perceptual systems implement hierarchical generative models, such as those discussed within the prediction error minimization framework. We build on existing treatments of representation via structural resemblance, such as those in Gładziejewski :559–582, 2016) and Gładziejewski and Miłkowski, to argue for a representationalist interpretation of the PEM framework. We further motivate the proposed approach to content by arguing that it (...) is consistent with approaches implicit in theories of unsupervised learning in neural networks. In the course of this discussion, we argue that the structural representation proposal, properly understood, has more in common with functional-role than with causal/informational or teleosemantic theories. In the remainder of the paper, we describe the PEM framework for approximate Bayesian inference in some detail, and discuss how structural representations might arise within the proposed Bayesian hierarchies. After explicating the notion of variational inference, we define a subjectively accessible measure of misrepresentation for hierarchical Bayesian networks by appeal to the Kullbach–Leibler divergence between posterior generative and approximate recognition densities, and discuss a related measure of objective misrepresentation in terms of correspondence with the facts. (shrink)

This paper presents a theoretical study of the binary oppositions underlying the mechanisms of natural computation understood as dynamical processes on natural information morphologies. Of special interest are the oppositions of discrete vs. continuous, structure vs. process, and differentiation vs. integration. The framework used is that of computing nature, where all natural processes at different levels of organisation are computations over informational structures. The interactions at different levels of granularity/organisation in nature, and the character of the phenomena that unfold through (...) those interactions, are modeled from the perspective of an observing agent. This brings us to the movement from binary oppositions to dynamic networks built upon mutually related binary oppositions, where each node has several properties. (shrink)

During the last decades, many cognitive architectures (CAs) have been realized adopting different assumptions about the organization and the representation of their knowledge level. Some of them (e.g. SOAR [35]) adopt a classical symbolic approach, some (e.g. LEABRA[ 48]) are based on a purely connectionist model, while others (e.g. CLARION [59]) adopt a hybrid approach combining connectionist and symbolic representational levels. Additionally, some attempts (e.g. biSOAR) trying to extend the representational capacities of CAs by integrating diagrammatical representations and reasoning are (...) also available [34]. In this paper we propose a reflection on the role that Conceptual Spaces, a framework developed by Peter G¨ardenfors [24] more than fifteen years ago, can play in the current development of the Knowledge Level in Cognitive Systems and Architectures. In particular, we claim that Conceptual Spaces offer a lingua franca that allows to unify and generalize many aspects of the symbolic, sub-symbolic and diagrammatic approaches (by overcoming some of their typical problems) and to integrate them on a common ground. In doing so we extend and detail some of the arguments explored by G¨ardenfors [23] for defending the need of a conceptual, intermediate, representation level between the symbolic and the sub-symbolic one. In particular we focus on the advantages offered by Conceptual Spaces (w.r.t. symbolic and sub-symbolic approaches) in dealing with the problem of compositionality of representations based on typicality traits. Additionally, we argue that Conceptual Spaces could offer a unifying framework for interpreting many kinds of diagrammatic and analogical representations. As a consequence, their adoption could also favor the integration of diagrammatical representation and reasoning in CAs. (shrink)

Localizing content in neural networks provides a bridge to understanding the way in which the brain stores and processes information. In this paper, I propose the existence of polytopes in the state space of the hidden layer of feedforward neural networks as vehicles of content. I analyze these geometrical structures from an information-theoretic point of view, invoking mutual information to help define the content stored within them. I establish how this proposal addresses the problem of misclassification and provide a novel (...) solution to the disjunction problem, which hinges on the precise nature of the causal-informational framework for content advocated herein. (shrink)

“There’s Plenty of Room at the Bottom”, said the title of Richard Feynman’s 1959 seminal conference at the California Institute of Technology. Fifty years on, nanotechnologies have led computer scientists to pay close attention to the links between physical reality and information processing. Not all the physical requirements of optimal computation are captured by traditional models—one still largely missing is reversibility. The dynamic laws of physics are reversible at microphysical level, distinct initial states of a system leading to distinct final (...) states. On the other hand, as von Neumann already conjectured, irreversible information processing is expensive: to erase a single bit of information costs ~3 × 10−21 joules at room temperature. Information entropy is a thermodynamic cost, to be paid in non-computational energy dissipation. This paper addresses the problem drawing on Edward Fredkin’s Finite Nature hypothesis: the ultimate nature of the universe is discrete and finite, satisfying the axioms of classical, atomistic mereology. The chosen model is a cellular automaton with reversible dynamics, capable of retaining memory of the information present at the beginning of the universe. Such a CA can implement the Boolean logical operations and the other building bricks of computation: it can develop and host all-purpose computers. The model is a candidate for the realization of computational systems, capable of exploiting the resources of the physical world in an efficient way, for they can host logical circuits with negligible internal energy dissipation. (shrink)

Morphological content (MC) is content that is implicit in the standing structure of the cognitive system. Henderson and Horgan claim that MC plays a distinctive epistemological role unrecognized by traditional epistemic theories. I consider the possibilities that MC plays this role either in central cognition or in peripheral modules. I argue that the peripheral MC does not play an interesting epistemological role and that the central MC is already recognized by traditional theories.

Functionalism of robot pain claims that what is definitive of robot pain is functional role, defined as the causal relations pain has to noxious stimuli, behavior and other subjective states. Here, I propose that the only way to theorize role-functionalism of robot pain is in terms of type-identity theory. I argue that what makes a state pain for a neuro-robot at a time is the functional role it has in the robot at the time, and this state is type identical (...) to a specific circuit state. Support from an experimental study shows that if the neural network that controls a robot includes a specific 'emotion circuit', physical damage to the robot will cause the disposition to avoid movement, thereby enhancing fitness, compared to robots without the circuit. Thus, pain for a robot at a time is type identical to a specific circuit state. (shrink)

Embedded and embodied approaches to cognition urge that (1) complicated internal representations may be avoided by letting features of the environment drive behavior, and (2) environmental structures can play an enabling role in cognition, allowing prior cognitive processes to solve novel tasks. Such approaches are thus in a natural position to oppose the ‘thesis of linguistic structuring’: The claim that the ability to use language results in a wholesale recapitulation of linguistic structure in onboard mental representation. Prominent examples of researchers (...) adopting this critical stance include Andy Clark, Michael Wheeler, and Mark Rowlands. But is such opposition warranted? Since each of these authors advocate accounts of mental representation that are broadly connectionist, I survey research on formal language computation in artificial neural networks, and argue that results indicate a strong form of the linguistic structuring thesis is true: Internal representational systems recapitulate significant linguistic structure, even on a connectionist account of mental representation. I conclude by sketching how my conclusion can nonetheless be viewed as consistent with and complimentary to an embedded/embodied account of the role of linguistic structure in cognition. (shrink)

Cognitive architectures are unified theories of cognition that take the form of computational formalisms. They support computational models that collectively account for large numbers of empirical regularities using small numbers of computational mechanisms. Empirical coverage and parsimony are the most prominent criteria by which architectures are designed and evaluated, but they are not the only ones. This paper considers three additional criteria that have been comparatively undertheorized. (a) Successful architectures possess subjective and intersubjective meaning, making cognition comprehensible to individual cognitive (...) scientists and organizing groups of like-minded cognitive scientists into genuine communities. (b) Successful architectures provide idioms that structure the design and interpretation of computational models. (c) Successful architectures are strange: They make provocative, often disturbing, and ultimately compelling claims about human information processing that demand evaluation. (shrink)

We examine Gärdenfors’ theory of conceptual spaces, a geometrical form of knowledge representation (Conceptual spaces: The geometry of thought, MIT Press, Cambridge, 2000 ), in the context of the general Creative Systems Framework introduced by Wiggins (J Knowl Based Syst 19(7):449–458, 2006a ; New Generation Comput 24(3):209–222, 2006 b ). Gärdenfors’ theory offers a way of bridging the traditional divide between symbolic and sub-symbolic representations, as well as the gap between representational formalism and meaning as perceived by human minds. We (...) discuss how both these qualities may be advantageous from the point of view of artificial creative systems. We take music as our example domain, and discuss how a range of musical qualities may be instantiated as conceptual spaces, and present a detailed conceptual space formalisation of musical metre. (shrink)

This book explores why, regarding practical reasoning, humans are sometimes still faster than artificial intelligence systems. It is the first to offer a self-contained presentation of neural network models for many computer science logics.

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)

Reformers urge that representation no longer earns its explanatory keep in cognitive science, and that it is time to discard this troublesome concept. In contrast, we hold that without representation cognitive science is utterly bereft of tools for explaining natural intelligence. In order to defend the latter position, we focus on the explanatory role of representation in computation. We examine how the methods of digital and analog computation are used to model a relatively simple target system, and show that representation (...) plays an in-eliminable explanatory role in both cases. We conclude that, to the extent that biologic systems engage in computation, representation is destined to play an explanatory role in cognitive science. (shrink)

The notion of a ‘symbol’ plays an important role in the disciplines of Philosophy, Psychology, Computer Science, and Cognitive Science. However, there is comparatively little agreement on how this notion is to be understood, either between disciplines, or even within particular disciplines. This paper does not attempt to defend some putatively ‘correct’ version of the concept of a ‘symbol.’ Rather, some terminological conventions are suggested, some constraints are proposed and a taxonomy of the kinds of issue that give rise to (...) disagreement is articulated. The goal here is to provide something like a ‘geography’ of the various notions of ‘symbol’ that have appeared in the various literatures, so as to highlight the key issues and to permit the focusing of attention upon the important dimensions. In particular, the relationship between ‘tokens’ and ‘symbols’ is addressed. The issue of designation is discussed in some detail. The distinction between simple and complex symbols is clarified and an apparently necessary condition for a system to be potentially symbol, or token bearing, is introduced. (shrink)

We argue that neural networks for semantic cognition, as proposed by Rogers & McClelland (R&M), do not acquire semantics and therefore cannot be the basis for a theory of semantic cognition. The reason is that the neural networks simply perform statistical categorization procedures, and these do not require any semantics for their successful operation. We conclude that this has severe consequences for the semantic cognition views of R&M.

The parallel distributed processing (PDP) perspective brings forward the important point that all semantic phenomena are based on analog underlying mechanisms, involving the weighted summation of multiple inputs by individual neurons. It falls short of indicating, however, how the essentially discrete nature of semantic processing may emerge at the cognitive level. Bridging this gap probably requires attractor networks.

Rogers & McClelland's (R&M's) précis represents an important effort to address key issues in concepts and categorization, but few of the simulations deliver what is promised. We argue that the models are seriously underconstrained, importantly incomplete, and psychologically implausible; more broadly, R&M dwell too heavily on the apparent successes without comparable concern for limitations already noted in the literature.

Bayesian models can be related to cognitive processes in a variety of ways that can be usefully understood in terms of Marr's distinction among three levels of explanation: computational, algorithmic and implementation. In this note, we discuss how an integrated probabilistic account of the different levels of explanation in cognitive science is resulting, at least for the current research practice, in a sort of unpredicted epistemological shift with respect to Marr's original proposal.

A similarity space is a hyperspace in which the dimensions represent various dimensions on which objects may differ. The similarity space theory of concepts is the thesis that concepts are regions of similarity spaces that are somehow realized in the brain. Proponents of such a theory of concepts include Paul Churchland and Peter Gärdenfors. This paper argues that the similarity space theory of concepts is mistaken because regions of similarity spaces cannot serve as the components of judgments. It emerges that (...) although similarity spaces cannot model concepts, they may model a kind of nonconceptual representation. (shrink)

This paper advocates explicitness about the type of entity to be considered as content- bearing in connectionist systems; it makes a positive proposal about how vehicles of content should be individuated; and it deploys that proposal to argue in favour of representation in connectionist systems. The proposal is that the vehicles of content in some connectionist systems are clusters in the state space of a hidden layer. Attributing content to such vehicles is required to vindicate the standard explanation for some (...) classificatory networks’ ability to generalise to novel samples their correct classification of the samples on which they were trained. (shrink)

Computer simulations show that an unstructured neural-network model [Shultz, T. R., & Bale, A. C. (2001). Infancy, 2, 501–536] covers the essential features␣of infant learning of simple grammars in an artificial language [Marcus, G. F., Vijayan, S., Bandi Rao, S., & Vishton, P. M. (1999). Science, 283, 77–80], and generalizes to examples both outside and inside of the range of training sentences. Knowledge-representation analyses confirm that these networks discover that duplicate words in the sentences are nearly identical and that they (...) use this near-identity relation to distinguish sentences that are consistent or inconsistent with a familiar grammar. Recent simulations that were claimed to show that this model did not really learn these grammars [Vilcu, M., & Hadley, R. F. (2005). Minds and Machines, 15, 359–382] confounded syntactic types with speech sounds and did not perform standard statistical tests of results. (shrink)

This collection offers an introduction to Churchland's work, as well as a critique of some of his most famous philosophical positions.

There is a gap between two different modes of computation: the symbolic mode and the subsymbolic (neuron-like) mode. The aim of this paper is to overcome this gap by viewing symbolism as a high-level description of the properties of (a class of) neural networks. Combining methods of algebraic semantics and non-monotonic logic, the possibility of integrating both modes of viewing cognition is demonstrated. The main results are (a) that certain activities of connectionist networks can be interpreted as non-monotonic inferences, and (...) (b) that there is a strict correspondence between the coding of knowledge in Hopfield networks and the knowledge representation in weight-annotated Poole systems. These results show the usefulness of non-monotonic logic as a descriptive and analytic tool for analyzing emerging properties of connectionist networks. Assuming an exponential development of the weight function, the present account relates to optimality theory – a general framework that aims to integrate insights from symbolism and connectionism. The paper concludes with some speculations about extending the present ideas. (shrink)

The past decade has witnessed the emergence of a novel stance on semantic representation, and its relationship to context sensitivity. Connectionist-minded philosophers, including Clark and van Gelder, have espoused the merits of viewing hidden-layer, context-sensitive representations as possessing semantic content, where this content is partially revealed via the representations'' position in vector space. In recent work, Bodén and Niklasson have incorporated a variant of this view of semantics within their conception of semantic systematicity. Moreover, Bodén and Niklasson contend that they (...) have produced experimental results which not only satisfy a kind of context-based, semantic systematicity, but which, to the degree that reality permits, effectively deals with challenges posed by Fodor and Pylyshyn (1988), and Hadley (1994a). The latter challenge involved well-defined criteria for strong semantic systematicity. This paper examines the relevant claims and experiments of Bodén and Niklasson. It is argued that their case fatally involves two fallacies of equivocation; one concerning ''semantic content'' and the other concerning ''novel test sentences''. In addition, it is argued that their ultimate construal of context sensitive semantics contains serious confusions. These confusions are also found in certain publications dealing with "latent semantic analysis". Thus, criticisms presented here have relevance beyond the work of Bodén and Niklasson. (shrink)

Any creature that must move around in its environment to find nutrients and mates, in order to survive and reproduce, faces the problem of sensorimotor control. A solution to this problem requires an on-board control mechanism that can shape the creature’s behaviour so as to render it “appropriate” to the conditions that obtain. There are at least three ways in which such a control mechanism can work, and Nature has exploited them all. The first and most basic way is for (...) a creature to bump into the things in its environment, and then, depending on what has been encountered, seek to modify its behaviour accordingly. Such an approach is risky, however, since some things in the environment are distinctly unfriendly. A second and better way, therefore, is for a creature to exploit ambient forms of energy that carry information about the distal structure of the environment. This is an improvement on the first method since it enables the creature to respond to the surroundings without actually bumping into anything. Nonetheless, this second method also has its limitations, one of which is that the information conveyed by such ambient energy is often impoverished, ambiguous and intermittent. (shrink)

Various systems that learn are examined to show how content is carried in connections installed by a learning history. Agents do not explicitly use the content of such states in practical reasoning, yet the content plays an important role in explaining behavior, and the physical state carrying that content plays a role in causing behavior, given other occurrent beliefs and desires. This leads to an understanding of the environmental reasons which are the determinate content of these states, and leads to (...) a better grasp of how representational content can be carried by systems without an explicit representation. (shrink)

It has been argued that neural networks and other forms of analog computation may transcend the limits of Turing-machine computation; proofs have been offered on both sides, subject to differing assumptions. In this article I argue that the important comparisons between the two models of computation are not so much mathematical as epistemological. The Turing-machine model makes assumptions about information representation and processing that are badly matched to the realities of natural computation (information representation and processing in or inspired by (...) natural systems). This points to the need for new models of computation addressing issues orthogonal to those that have occupied the traditional theory of computation. (shrink)

In this paper I discuss one of the key issuesin the philosophy of neuroscience:neurosemantics. The project of neurosemanticsinvolves explaining what it means for states ofneurons and neural systems to haverepresentational contents. Neurosemantics thusinvolves issues of common concern between thephilosophy of neuroscience and philosophy ofmind. I discuss a problem that arises foraccounts of representational content that Icall ``the economy problem'': the problem ofshowing that a candidate theory of mentalrepresentation can bear the work requiredwithin in the causal economy of a mind and (...) anorganism. My approach in the current paper isto explore this and other key themes inneurosemantics through the use of computermodels of neural networks embodied and evolvedin virtual organisms. The models allow for thelaying bare of the causal economies of entireyet simple artificial organisms so that therelations between the neural bases of, forinstance, representation in perception andmemory can be regarded in the context of anentire organism. On the basis of thesesimulations, I argue for an account ofneurosemantics adequate for the solution of theeconomy problem. (shrink)

Although visual long-term memory (VLTM) and visual short-term memory (VSTM) can be distinguished from each other (and from visual sensory storage [SS]), they are embodied within the same modality-specific brain regions, but in very different ways: VLTM as patterns of connectivity and VSTM as patterns of activity. Perception and VSTM do not “activate” VLTM. They use VLTM to create novel patterns of activity relevant to novel circumstances.

Ramsey (1997) argues that connectionist representations 'do not earn their explanatory keep'. The aim of this paper is to examine the argument Ramsey gives to support that conclusion. In doing so, I identify two kinds of explanatory need—need relative to a possible explanation and need relative to a true explanation and argue that internal representations are not needed for either connectionist or nonconnectionist possible explanations but that it is quite likely that they are needed for true explanations. However, to show (...) that the latter is the case requires more than a consideration of the form of explanation involved. (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)

Two different but closely related issues in current cognitive science will be considered in this essay. One is the controversial and extensively discussed question of how connectionist and symbolic representations of knowledge are related to each other. The other concerns the notion of connectionist learning and its relevance for the understanding of the distinction between propositional and nonpropositional knowledge. More specifically, I shall give an overview of a result in Rantala and Vadén (1994) establishing a limiting case correspondence between symbolic (...) and connectionist representations and, on the other hand, study the problem, preliminarily investigated in Rantala (1998), of how propositional knowledge may arise from nonpropositional knowledge. I shall also try to point out that on some more or less plausible assumptions, often made by cognitive scientists, these results may have some significance when we try to comprehend the nature of human knowledge representation. Some of these assumptions are rather hypothethical and debatable for the time being and they will become justified in the future only if there will be more progress in the empirical and theoretical research on the brain and on artificial networks. The assumptions concern, besides some questions of the behavior of neural networks, such things as the relevance of pattern recognition for modelling human cognition, in particular, knowledge acquisition, and the relation between emergence and reduction. (shrink)

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

Jerry Fodor and Ernest Lepore [(1992) Holism: a shopper's guide, Oxford: Blackwell; (1996) in R. McCauley (Ed.) The Churchlands and their critics , Cambridge: Blackwell] have launched a powerful attack against Paul Churchland's connectionist theory of semantics--also known as state space semantics. In one part of their attack, Fodor and Lepore argue that the architectural and functional idiosyncrasies of connectionist networks preclude us from articulating a notion of conceptual similarity applicable to state space semantics. Aarre Laakso and Gary Cottrell [(1998) (...) in M. A. Gernsbacher & S. Derry (Eds) Proceedings of the 20th Annual Conference of the Cognitive Science Society, Mahway, NJ: Erlbaum; Philosophical Psychology ] 13, 47-76 have recently run a number of simulations on simple feedforward networks and applied a mathematical technique for measuring conceptual similarity in the representational spaces of those networks. Laakso and Cottrell contend that their results decisively refute Fodor and Lepore's criticisms. Paul Churchland [(1998) Journal of Philosophy, 95, 5-32 ] goes further. He uses Laakso and Cottrell's neurosimulations to argue that connectionism does furnish us with all we need to construct a robust theory of semantics and a robust theory of translation. In this paper I shall argue that whereas Laakso and Cottrell's neurocomputational results may provide us with a rebuttal of Fodor and Lepore's argument, Churchland's conclusion is far too optimistic. In particular, I shall try to show that connectionist modelling does not provide any objective criterion for achieving a one-to-one accurate translational mapping across networks. (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)