Beyond the exclusively propositional era

Contemporary epistemology has assumed that knowledge is represented in sentences or propositions. However, a variety of extensions and alternatives to this view have been proposed in other areas of investigation. We review some of these proposals, focusing on (1) Ryle's notion of knowing how and Hanson's and Kuhn's accounts of theory-laden perception in science; (2) extensions of simple propositional representations in cognitive models and artificial intelligence; (3) the debate concerning imagistic versus propositional representations in cognitive psychology; (4) recent treatments of concepts and categorization which reject the notion of necessary and sufficient conditions; and (5) parallel distributed processing (connectionist) models of cognition. This last development is especially promising in providing a flexible, powerful means of representing information nonpropositionally, and carrying out at least simple forms of inference without rules. Central to several of the proposals is the notion that much of human cognition might consist in pattern recognition rather than manipulation of rules and propositions.The preparation of this article was supported in part by National Institutes of Health Grants No. NICHD-19265 and NICHD-06016. We would like to thank Rita Anderson, David Blumenfeld, Robert McCauley, and Patricia Siple for helpful discussions on points in this paper.     

Cognitive neuroimaging: cognitive science out of the armchair

Cognitive scientists were not quick to embrace the functional neuroimaging technologies that emerged during the late 20th century. In this new century, cognitive scientists continue to question, not unreasonably, the relevance of functional neuroimaging investigations that fail to address questions of interest to cognitive science. However, some ultra-cognitive scientists assert that these experiments can never be of relevance to the study of cognition. Their reasoning reflects an adherence to a functionalist philosophy that arbitrarily and purposefully distinguishes mental information-processing systems from brain or brain-like operations. This article addresses whether data from properly conducted functional neuroimaging studies can inform and subsequently constrain the assumptions of theoretical cognitive models. The article commences with a focus upon the functionalist philosophy espoused by the ultra-cognitive scientists, contrasting it with the materialist philosophy that motivates both cognitive neuroimaging investigations and connectionist modelling of cognitive systems. Connectionism and cognitive neuroimaging share many features, including an emphasis on unified cognitive and neural models of systems that combine localist and distributed representations. The utility of designing cognitive neuroimaging studies to test (primarily) connectionist models of cognitive phenomena is illustrated using data from functional magnetic resonance imaging (fMRI) investigations of language production and episodic memory.     

Consciousness: converging insights from connectionist modeling and neuroscience

Over the past decade, many findings in cognitive neuroscience have resulted in the view that selective attention, working memory and cognitive control involve competition between widely distributed representations. This competition is biased by top-down projections (notably from prefrontal cortex), which can selectively enhance some representations over others. This view has now been implemented in several connectionist models. In this review, we emphasize the relevance of these models to understanding consciousness. Interestingly, the models we review have striking similarities to others directly aimed at implementing 'global workspace theory'. All of these models embody a fundamental principle that has been used in many connectionist models over the past twenty years: global constraint satisfaction.     

Multiple levels of inquiry in cognitive science

Summary Gibsonian ecological psychology, symbolic information processing, and connectionist information processing are frequently construed as three competing paradigms or research traditions, each seeking dominance in experimental psychology and in cognitive science generally. There is an important element of truth in this perspective, and any adequate account of the development of experimental psychology over the past 30 years would have to examine seriously how the various conceptual frameworks, experimental endeavors, and social institutions have figured in this conflict. But the goal of this paper is not to characterize the historical dynamics within experimental psychology and cognitive science; rather, it is to consider what sorts of rapprochement is possible. Rapprochement, however, is not sought simply for its own sake or out of an a priori conviction that scientific enterprises should be unified. Spirited controversy between competing traditions is often an important component of progess (Laudan, 1977). Rapprochement has a purpose when alternative theoretical traditions have reached a point when each confronts serious shortcomings that can best be overcome by incorporating alternative perspectives. In this paper I try to show that this is the situation that exists in experimental psychology and cognitve science generally with respect to the three traditions enumerated above. I first explore how cognitive inquiry directed at internal procedures for processing information could benefit from a detailed study of the context of cognition, including insights provided by the Gibsonian tradition. Second, I examine the current controversy between symbolic and connectionist approaches and address the question of what contributions each offers to the other. Finally, I offer a framework in which multiple levels of inquiry in cognitve science can be related.     

Natural deduction in connectionist systems

The relation between logic and thought has long been controversial, but has recently influenced theorizing about the nature of mental processes in cognitive science. One prominent tradition argues that to explain the systematicity of thought we must posit syntactically structured representations inside the cognitive system which can be operated upon by structure sensitive rules similar to those employed in systems of natural deduction. I have argued elsewhere that the systematicity of human thought might better be explained as resulting from the fact that we have learned natural languages which are themselves syntactically structured. According to this view, symbols of natural language are external to the cognitive processing system and what the cognitive system must learn to do is produce and comprehend such symbols. In this paper I pursue that idea by arguing that ability in natural deduction itself may rely on pattern recognition abilities that enable us to operate on external symbols rather than encodings of rules that might be applied to internal representations. To support this suggestion, I present a series of experiments with connectionist networks that have been trained to construct simple natural deductions in sentential logic. These networks not only succeed in reconstructing the derivations on which they have been trained, but in constructing new derivations that are only similar to the ones on which they have been trained.     

Hybrid preference machines based on inspiration from neuroscience

In the past, a variety of computational problems have been tackled with different connectionist network approaches. However, very little research has been done on a framework which connects neuroscience-inspired models with connectionist models and higher level symbolic processing. In this paper, we outline a preference machine framework which focuses on a hybrid integration of various neural and symbolic techniques in order to address how we may process higher level concepts based on concepts from neuroscience. It is a first hybrid framework which allows a link between spiking neural networks, connectionist preference machines and symbolic finite state machines. Furthermore, we present an example experiment on interpreting a neuroscience-inspired network by using preferences which may be connected to connectionist or symbolic interpretations.     

Challenging the widespread assumption that connectionism and distributed representations go hand-in-hand

One of the central claims associated with the parallel distributed processing approach popularized by D.E. Rumelhart, J.L. McClelland and the PDP Research Group is that knowledge is coded in a distributed fashion. Localist representations within this perspective are widely rejected. It is important to note, however, that connectionist networks can learn localist representations and many connectionist models depend on localist coding for their functioning. Accordingly, a commitment to distributed representations should be considered a specific theoretical claim regarding the structure of knowledge rather than a core principle, as often assumed. In this paper, it is argued that there are fundamental computational and empirical challenges that have not yet been addressed by distributed connectionist theories that are readily accommodated within localist approaches. This is highlighted in the context of modeling word and nonword naming, the domain in which some of the strongest claims have been made. It is shown that current PDP models provide a poor account of naming monosyllable items, and that distributed representations make it difficult for these models to scale up to more complex language phenomena. At the same time, models that learn localist representations are shown to hold promise in supporting many of the core reading and language functions on which PDP models fail. It is concluded that the common rejection of localist coding schemes within connectionist architectures is premature.     

The Contents of Perception and the Contents of Emotion

Several philosophers think there are important analogies between emotions and perceptual states. Furthermore, considerations about the rational assessibility of emotions have led philosophers—in some cases, the very same philosophers—to think that the content of emotions must be propositional content. If one finds it plausible that perceptual states have propositional contents, then there is no obvious tension between these views. However, this view of perception has recently been attacked by philosophers who hold that the content of perception is object‐like. I shall argue for a view about the content of emotions and perceptual states which will enable us to hold both that emotional content is analogous to perceptual content and that both emotions and perceptual states can have propositional contents. This will involve arguing for a pluralist view of perceptual content, on which perceptual states can have both contents which are proposition‐like and contents which are object‐like. I shall also address two significant objections to the claim that emotions can have proposition‐like contents. Meeting one of these objections will involve taking on a further commitment: the pluralist account of perceptual content will have to be one on which the contents of perception can be non‐conceptual.     

Methods,minds, memory,and kinds

ABSTRACT

The acquisition of a skill, or knowledge-how, on the one hand, and the acquisition of a piece of propositional knowledge on the other, appear to be different sorts of epistemic achievements. Does this difference lie in the nature of the knowledge involved, marking a joint between knowledge-how and propositional knowledge? Intellectualists say no: All knowledge is propositional knowledge. Anti-intellectualists say yes: Knowledge-how and propositional knowledge are different in kind. What resources or methods may we legitimately and fruitfully employ to adjudicate this debate? What is (or are) the right way(s) to show the nature of the knowledge knowers know? Here too there is disagreement. I defend the legitimacy of the anti-intellectualist appeal to cognitive neuroscientific findings against a recent claim that anti-intellectualists conflate the scientific categories of procedural and declarative knowledge with the mental kinds of skill (knowledge-how) and propositional knowledge, respectively. I identify two kinds of arguments for this claim and argue that neither succeeds.     

Logic programs and connectionist networks

One facet of the question of integration of Logic and Connectionist Systems, and how these can complement each other, concerns the points of contact, in terms of semantics, between neural networks and logic programs. In this paper, we show that certain semantic operators for propositional logic programs can be computed by feedforward connectionist networks, and that the same semantic operators for first-order normal logic programs can be approximated by feedforward connectionist networks. Turning the networks into recurrent ones allows one also to approximate the models associated with the semantic operators. Our methods depend on a well-known theorem of Funahashi, and necessitate the study of when Funahashi's theorem can be applied, and also the study of what means of approximation are appropriate and significant.     

Knowledge and abilities: The need for a new understanding of knowing-how

Stanley and Williamson (The Journal of Philosophy 98(8), 411–444 2001) reject the fundamental distinction between what Ryle once called ‘knowing-how’ and ‘knowing-that’. They claim that knowledge-how is just a species of knowledge-that, i.e. propositional knowledge, and try to establish their claim relying on the standard semantic analysis of ‘knowing-how’ sentences. We will undermine their strategy by arguing that ‘knowing-how’ phrases are under-determined such that there is not only one semantic analysis and by critically discussing and refuting the positive account of knowing-how they offer. Furthermore, we argue for an extension of the classical ‘knowing-how’/‘knowing-that’-dichotomy by presenting a new threefold framework: Using some core-examples of the recent debate, we will show that we can analyze knowledge situations that are not captured by the Rylean dichotomy and argue that, therefore, the latter has to be displaced by a more fine-grained theory of knowledge-formats. We will distinguish three different formats of knowledge we can have of our actions, namely (1) propositional, (2) practical, and (3) image-like formats of knowledge. Furthermore, we will briefly analyze the underlying representations of each of these knowledge-formats.     

The Value of Symbolic Computation

Standard generative linguistic theory, which uses discrete symbolic models of cognition, has some strengths and weaknesses. It is strong on providing a network of outposts that make scientific travel in the jungles of natural language feasible. It is weak in that it currently depends on the elaborate and unformalized use of intuition to develop critical supporting assumptions about each data point. In this regard, it is not in a position to characterize natural language systems in the lawful terms that ecological psychologists strive for. Connectionist learning models offer some help: They define lawful relations between linguistic environments and language systems. But our understanding of them is currently weak, especially when it comes to natural language syntax. Fortunately, symbolic linguistic analysis can help connectionism if the two meet via dynamical systems theory. I discuss a case in point: Insights from linguistic explorations of natural language syntax appear to have identified information structures that are particularly relevant to understanding ecologically appealing but analytically mysterious connectionist learning models.     

Coherence and Truth: A Cognitive Model of Propositional Truth Attribution

The truth value assigned to a proposition is treated by philosophers, logicians, and most psychologists as an abstract construct, a theoretical object outside the cognitive system. Breaking away from this consensus, we propose to carry out a psychological investigation to analyse the objective, verifiable properties of representations categorized as true by human individuals. We shall reject the conception whereby attributing a truth value to a proposition is the result of the activation of knowledge about the truth of that proposition. We shall also exclude the conception of truth as the result of the establishment of a correspondence with the world. We propose that truth be understood as the result of a decision about the values taken on by the conditions for fulfilment of the act of referencing in a mental model. Our cognitive model of propositional truth attribution is built on the assumption that the truth value of a proposition is determined by the ability of that proposition to fit into the theory of the field to which it refers. This attribution is viewed as a two-stage cognitive activity. During the first stage, the features defining the coherence of the proposition in the activated mental model determine its plausibility value. This defines a generally inconsistent set of truth candidates. The second stage involves selecting the subset containing all propositions which, in context, will be considered true. Two selection criteria are used: maximum consistency and connectivity. The preliminary experimental results proved to be compatible with the proposed model.     

Catastrophic forgetting in connectionist networks

All natural cognitive systems, and, in particular, our own, gradually forget previously learned information. Plausible models of human cognition should therefore exhibit similar patterns of gradual forgetting of old information as new information is acquired. Only rarely does new learning in natural cognitive systems completely disrupt or erase previously learned information; that is, natural cognitive systems do not, in general, forget ‘catastrophically’. Unfortunately, though, catastrophic forgetting does occur under certain circumstances in distributed connectionist networks. The very features that give these networks their remarkable abilities to generalize, to function in the presence of degraded input, and so on, are found to be the root cause of catastrophic forgetting. The challenge in this field is to discover how to keep the advantages of distributed connectionist networks while avoiding the problem of catastrophic forgetting. In this article the causes, consequences and numerous solutions to the problem of catastrophic forgetting in neural networks are examined. The review will consider how the brain might have overcome this problem and will also explore the consequences of this solution for distributed connectionist networks.     

Dynamical approaches to cognitive science

Dynamical ideas are beginning to have a major impact on cognitive science, from foundational debates to daily practice. In this article, I review three contrasting examples of work in this area that address the lexical and grammatical structure of language, Piaget's classic 'A-not-B' error, and active categorical perception in an embodied, situated agent. From these three examples, I then attempt to articulate the major differences between dynamical approaches and more traditional symbolic and connectionist approaches. Although the three models reviewed here vary considerably in their details, they share a focus on the unfolding trajectory of a system's state and the internal and external forces that shape this trajectory, rather than the representational content of its constituent states or the underlying physical mechanisms that instantiate the dynamics. In some work, this dynamical viewpoint is augmented with a situated and embodied perspective on cognition, forming a promising unified theoretical framework for cognitive science broadly construed.     

Connectionist models of neuropsychological disorders

Artificial neural networks ('connectionist models') embody aspects of real neuronal systems. But does studying the breakdown of performance in such models help us to understand cognitive impairments in humans following brain damage? Here we review recent attempts to capture different neuropsychological disorders using connectionist models with simulated lesions. We show how such lesion studies can be used to evaluate some of the standard assumptions made in neuropsychological research, concerning both double dissociations and associations between patterns of impairment. We also illustrate how lesioned models, like humans, can sometimes be more impaired on the easier of two tasks and demonstrate that connectionist models can incorporate forms of internal structure. Finally we discuss the utility of the models for understanding and predicting the effectiveness of different rehabilitation strategies. Future questions concern the role and possible development of internal structure within these models, whether the models can be generalized to larger-scale simulations, and whether they can accommodate higher-order linguistic disorders.     

Learning new faces in an interactive activation and competition model

Abstract

Certain contemporary accounts of object and face recognition use connectionist networks with local representations. This paper describes and extends one such account: an interactive activation and competition (IAC) model of face recognition. In contrast to many networks with distributed representations, IAC models do not incorporate a learning mechanism. This limits their use in psychological modelling. This paper describes how a learning mechanism can be built into an IAC model. The mechanism automatically learns new representations and appears to have many of the desirable properties traditionally associated with distributed networks. Some simulations that produce results consistent with our knowledge of human face learning are reported. Finally, the relation between this work and current theories of visual object recognition is discussed.