This article presents counter evidence against Smolensky's theory that human intuitive/nonconscious congnitive processes can only be accurately explained in terms of subsymbolic computations carried out in artificial neural networks. We presentsymboliclearning models of two well‐studied, complicated cognitive tasks involving nonconscious acquisition of information: learning production rules and artificial finite state grammars. Our results demonstrate that intuitive learning does not imply subsymbolic computation, and that the already well‐established, perceived correlation between “conscious” and “symbolic” on the one hand, and between (...) “nonconscious” and “subsymbolic” on the other, does not exist. (shrink)

To deal with reactive sequential decision tasks we present a learning model Clarion which is a hybrid connectionist model consisting of both localist and dis tributed representations based on the two level ap proach proposed in Sun The model learns and utilizes procedural and declarative knowledge tapping into the synergy of the two types of processes It uni es neural reinforcement and symbolic methods to perform on line bottom up learning Experiments in various situations are reported that shed light (...) on the working of the model.. (shrink)

Supporters of eliminative connectionism have argued for a pattern association-based explanation of language learning and language processing. They deny that explicit rules and symbolic representations play any role in language processing and cognition in general. Their argument is based to a large extent on two artificial neural network (ANN) models that are claimed to be able to learn the past tenses of English verbs (Rumelhart & McClelland, 1986, Parallel distributed processing, Vol. 2, Cambridge, MA: MIT Press; MacWhinney & (...) Leinbach, 1991, Cognition, 40, 121-157). In this article we critically review Rumelhart and McClelland's as well as MacWhinney and Leinbach's ANN models and conclude that they do not succeed in the assigned task of learning the past tenses of English verbs. In order to answer their challenge to the symbolic processing approach, we present our symbolic pattern associator (SPA)-a general-purpose pattern associator that can learn to associate arbitrary discrete patterns. We carried out several experiments with the SPA using the same set of verbs that was used in MacWhinney and Leinbach's simulation with more realistic training and testing procedures. The SPA outperformed the connectionist models by a wide margin in the accuracy of learning, and successful inductive generalizations to unseen verbs. Our SPA has very natural and psychologically realistic explanations to many psychological effects such as U-shaped learning curve, and is much closer to human subjects in predicting past tense of the pseudo-verbs. In contrast to ANNs, whose internal representations are entirely opaque, the SPA can represent the acquired knowledge in the form of production rules that allow for further higher-level processing and integration, resulting in linguistically realistic associative templates for irregular verbs and production rules for regular verbs. In the light of these findings, we conclude that eliminative connectionists' vision of cognition as simple pattern association and pattern recognition without symbolic representation is inadequate. Pattern association as such does not imply rule-less or cue-based models of language acquisition or of human learning in general. (shrink)

The ability to combine words into novel sentences has been used to argue that humans have symbolic language production abilities. Critiques of connectionist models of language often center on the inability of these models to generalize symbolically (Fodor & Pylyshyn, 1988; Marcus, 1998). To address these issues, a connectionist model of sentence production was developed. The model had variables (role‐concept bindings) that were inspired by spatial representations (Landau & Jackendoff, 1993). In order to take advantage of these (...) variables, a novel dual‐pathway architecture with event semantics is proposed and shown to be better at symbolic generalization than several variants. This architecture has one pathway for mapping message content to words and a separate pathway that enforces sequencing constraints. Analysis of the model's hidden units demonstrated that the model learned different types of information in each pathway, and that the model's compositional behavior arose from the combination of these two pathways. The model's ability to balance symbolic and statistical behavior in syntax acquisition and to model aphasic double dissociations provided independent support for the dual‐pathway architecture. (shrink)

Together, Models and Computability and its sister volume Sets and Proofs will provide readers with a comprehensive guide to the current state of mathematical logic. All the authors are leaders in their fields and are drawn from the invited speakers at 'Logic Colloquium '97' (the major international meeting of the Association of Symbolic Logic). It is expected that the breadth and timeliness of these two volumes will prove an invaluable and unique resource for specialists, post-graduate researchers, and the (...) informed and interested nonspecialist. (shrink)

1.1 The predominant approach to cognitive modeling is still what has come to be called "computationalism" (Dietrich 1990, Harnad 1990b), the hypothesis that cognition is computation. The more recent rival approach is "connectionism" (Hanson & Burr 1990, McClelland & Rumelhart 1986), the hypothesis that cognition is a dynamic pattern of connections and activations in a "neural net." Are computationalism and connectionism really deeply different from one another, and if so, should they compete for cognitive hegemony, or should they collaborate? These (...) questions will be addressed here, in the context of an obstacle that is faced by computationalism (as well as by connectionism if it is either computational or seeks cognitive hegemony on its own): The symbol grounding problem (Harnad 1990). (shrink)

The ability of predicting upcoming events or conditions in advance offers substantial selective advantage to living beings. The most successful systematic tool for fairly reliable prognoses is the use of dynamical causal models in combination with memorised experience. Surprisingly, causality is a fundamental but rather controversially disputed concept. For both models and memory, symbol processing is requisite. Symbols are a necessary and sufficient attribute of life from its very beginning; the process of their evolutionary emergence was discovered by (...) Julian Huxley a century ago. In behavioural biology, this universal symmetry-breaking kinetic phase transition became known as ritualisation. Symbol use for predicting future dynamical processes has culminated in the unprecedented complexity of mental models used in science and technology, coining the historical ascent of modern humans. Observation and measurement transform structural information of physical exchange processes into symbolic information from which state quantities are derived by means of mental models. However, phylogenetically inherited models such as naïve realism do not necessarily explain the sophisticated insights revealed by modern experiments with, say, entangled quantum states. It is suggested to carefully distinguish observed exchange quantities from predicted unobservable state quantities, and physical reality from mental models thereof. (shrink)

In this paper I argue against a deflationist view that as representational vehicles symbols and models do their jobs in essentially the same way. I argue that symbols are conventional vehicles whose chief function is denotation while models are epistemic vehicles whose chief function is showing what their targets are like in the relevant aspects. It is further pointed out that models usually do not rely on similarity or some such relations to relate to their targets. For (...) that referential relation they reply instead on symbols (names and labels) given to them and their parts. And a Goodmanian view on pictures of fictional characters reveals the distinction between symbolic and model representations. (shrink)

In the first section of the article, we examine some recent criticisms of the connectionist enterprise: first, that connectionist models are fundamentally behaviorist in nature (and, therefore, non-cognitive), and second that connectionist models are fundamentally associationist in nature (and, therefore, cognitively weak). We argue that, for a limited class of connectionist models (feed-forward, pattern-associator models), the first criticism is unavoidable. With respect to the second criticism, we propose that connectionist modelsare fundamentally associationist but that this is (...) appropriate for building models of human cognition. However, we do accept the point that there are cognitive capacities for which any purely associative model cannot provide a satisfactory account. The implication that we draw from is this is not that associationist models and mechanisms should be scrapped, but rather that they should be enhanced.In the next section of the article, we identify a set of connectionist approaches which are characterized by “active symbols” — recurrent circuits which are the basis of knowledge representation. We claim that such approaches avoid criticisms of behaviorism and are, in principle, capable of supporting full cognition. In the final section of the article, we speculate at some length about what we believe would be the characteristics of a fully realized active symbol system. This includes both potential problems and possible solutions (for example, mechanisms needed to control activity in a complex recurrent network) as well as the promise of such systems (in particular, the emergence of knowledge structures which would constitute genuine internal models). (shrink)

Historians of science find it difficult to pinpoint to an exact period in which symbolic algebra came into existence. This can be explained partly because the historical process leading to this breakthrough in mathematics has been a complex and diffuse one. On the other hand, it might also be the case that in the early twentieth century, historians of mathematics over emphasized the achievements in algebraic procedures and underestimated the conceptual changes leading to symbolic algebra. This paper attempts (...) to provide a more precise setting for the historical context in which this decisive step to symbolic reasoning took place. For that purpose we will consider algebraic problem solving as model-based reasoning and symbolic representation as a model. This allows us to characterize the emergence of symbolic algebra as a shift from a geometrical to a symbolic mode of representation. The use of the symbolic as a model will be situated in the context of mercantilism where merchant activity of exchange has led to reciprocal relations between money and wealth. (shrink)

Localist networks are symbolic models, because their nodes refer to extra-mental objects and events. Hence, localist networks can be combined with symbolic computations to form hybrid models. Such models are already familiar and they are likely to represent the dominant type of cognitive model in the next few decades.

Hemispatial neglect in imagery implies a spatially organised representation. Reaction times in memory for arrays of locations from shifted viewpoints indicate processes analogous to actual bodily movement through space. Behavioral data indicate a privileged role for this process in memory. A proposed spatial mechanism makes contact with direct recordings of the representations of location and orientation in the mammalian brain.

//static.cambridge.org/content/id/urn%3Acambridge.org%3Aid%3Aarticle%3AS0022481200044376/resource/na me/firstPage-S0022481200044376a.jpg.

This book brings together several directions of work in model theory between the late 1950s and early 1980s.

There has been much discussion recently about the scope and limits of purely symbolic models of the mind and about the proper role of connectionism in cognitive modeling. This paper describes the symbol grounding problem : How can the semantic interpretation of a formal symbol system be made intrinsic to the system, rather than just parasitic on the meanings in our heads? How can the meanings of the meaningless symbol tokens, manipulated solely on the basis of their shapes, (...) be grounded in anything but other meaningless symbols? The problem is analogous to trying to learn Chinese from a Chinese/Chinese dictionary alone. A candidate solution is sketched: Symbolic representations must be grounded bottom-up in nonsymbolic representations of two kinds: iconic representations, which are analogs of the proximal sensory projections of distal objects and events, and categorical representations, which are learned and innate feature-detectors that pick out the invariant features of object and event categories from their sensory projections. Elementary symbols are the names of these object and event categories, assigned on the basis of their categorical representations. Higher-order symbolic representations, grounded in these elementary symbols, consist of symbol strings describing category membership relations. Connectionism is one natural candidate for the mechanism that learns the invariant features underlying categorical representations, thereby connecting names to the proximal projections of the distal objects they stand for. In this way connectionism can be seen as a complementary component in a hybrid nonsymbolic/symbolic model of the mind, rather than a rival to purely symbolic modeling. Such a hybrid model would not have an autonomous symbolic module, however; the symbolic functions would emerge as an intrinsically dedicated symbol system as a consequence of the bottom-up grounding of categories ' names in their sensory representations. Symbol manipulation would be governed not just by the arbitrary shapes of the symbol tokens, but by the nonarbitrary shapes of the icons and category invariants in which they are grounded. (shrink)

Our aim is to solve a quite old question on the difference between expandability and compact expandability. Toward this, we further investigate the logic of countable cofinality.

Meta-learning is even more broadly relevant to the study of inductive biases than Binz et al. suggest: Its implications go beyond the extensions to rational analysis that they discuss. One noteworthy example is that meta-learning can act as a bridge between the vector representations of neural networks and the symbolic hypothesis spaces used in many Bayesian models.