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 (arbitrary) 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: (1) "iconic representations" , which are analogs of the proximal sensory projections of distal objects and events, and (2) "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 (nonsymbolic) categorical representations. Higher-order (3) "symbolic representations" , grounded in these elementary symbols, consist of symbol strings describing category membership relations (e.g., "An X is a Y that is Z"). 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 ...

In the past, nearest neighbor algorithms for learning from examples have worked best in domains in which all features had numeric values. In such domains, the examples can be treated as points and distance metrics can use standard definitions. In symbolic domains, a more sophisticated treatment of the feature space is required. We introduce a nearest neighbor algorithm for learning in domains with symbolic features. Our algorithm calculates distance tables that allow it to produce real-valued distances between instances, and attaches weights to the instances to further modify the structure of feature space. We show that this technique produces excellent classification accuracy on three problems that have been studied by machine learning researchers: predicting protein secondary structure, identifying DNA promoter sequences, and pronouncing English text. Direct experimental comparisons with the other learning algorithms show that our nearest neighbor algorithm is comparable or superior ...

Abstract not found

Searle's celebrated Chinese Room Argument has shaken the foundations of Artificial Intelligence. Many refutations have been attempted, but none seem convincing. This paper is an attempt to sort out explicitly the assumptions and the logical, methodological and empirical points of disagreement. Searle is shown to have underestimated some features of computer modeling, but the heart of the issue turns out to be an empirical question about the scope and limits of the purely symbolic (computational) model of the mind. Nonsymbolic modeling turns out to be immune to the Chinese Room Argument. The issues discussed include the Total Turing Test, modularity, neural modeling, robotics, causality and the symbol-grounding problem. 1.

Neural networks have received a great deal of attention over the last few years. They are being used in the areas of prediction and classification; areas where regression models and other related statistical techniques have traditionally been used. In this paper, we discuss neural networks and compare them to regression models. We start by exploring the history of neural networks. This includes a review of relevant literature on the topic of neural networks. Neural network nomenclature is then introduced and the backpropagation algorithm, the most widely used learning algorithm, is derived and explained in detail. A comparison between regression analysis and neural networks in terms of notation and implementation is conducted to aid the reader in understanding neural networks. We compare the performance of regression analysis with that of neural networks on two simulated examples and one example on a large data set. We show that neural networks act as a type of nonparametric regression...

This paper explores the perception and well-formedness of nonsense words containing nasal-obstruent (NO) clusters. Morpheme internally, these clusters are subject to a homorganicity constraint in English, which would be represented in a conventional phonology by a feature spreading rule. Yet such a rule does not do justice to the lexical statistics. The strength of the homorganicity requirement depends on the manner of the obstruent and the place of articulation of both the nasal and the obstruent. Some NO clusters are therefore extremely frequent (e.g. /nt/), others are unattested (/m7/) , and yet others fall between these two extremes (/nf/). Because NO clusters are a phonetically coherent set, and sample the range of frequencies finely, they make Hay, Pierrehumbert and Beckman

This paper compares and contrasts two forms of distributed cognition - one looking at how an individual interacts with one or more artefacts, the other looking at how groups of people interact with or without artefacts. Whilst the two approaches have many similarities, they can be seen to have significant practical and theoretical differences and merit very different approaches, particularly in their application.

ions are regularities that best describe the structure of the data. It might be possible to devise a self-organizing process that is sensitive to the internal structure of the training examples. The network would learn the processing task, and at the same time develop a layout of rules, schemas, and other abstract structures that best describe the data. Further input would then be interpreted and represented in terms of this layout (i.e., in terms of the internal structure of the input). Such a capacity would be a major step toward extending subsymbolic AI beyond the limitations of current models. 11 Conclusion Above all, DISCERN serves to show that subsymbolic high-level AI is feasible. DISCERN constitutes a first implementation of the integrated connectionist approach, demonstrating that it is possible to build complete models from independently designed connectionist components. The scale-up properties of the approach seem quite good. Hierarchical modular structure with sequential ...

Distributed cognition provides a means of describing the co-ordination of collaborative activity. A single framework is applied to examine the interactions between people, the tools they use, and the environments that their activities are situated within. The resultant analyses show how the system resources are applied to result in problem solving activity. Examples from fieldwork are used to explore these issues. The paper critically evaluates DC, exploring the problems and the benefits that such an approach brings to understanding the organisation of information in its contexts.

tational methods for the transformation of machine readable dictionaries (MRDs) into machine tractable dictionaries, i.e., MRDs eonvert6d into a format usable for natural language processing tasks. The MRD used is The Longman Dictionary of Contemporary English.