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)

This volume tackles the slippery subject of 'meaning'.

It is argued that complexity has only a limited use as a paradigm against reductionist approaches and that it has a much richer potential as a comparable property. What can complexity be usefully said to be a property of is discussed. It is argued that it is unlikely to have any useful value as applied to real object or systems. Further that even relativising it to an observer has problems. It is proposed that complexity can be only usefully applied to (...) constructions within a given language. It is argued that complexity is usefully differentiated from the concepts of size, ignorance, variety, minimum description length and order. A definition of complexity is proposed which can be summarised as follows: That property of a language expression which makes it difficult to formulate its overall behaviour even when given almost complete information about its atomic components and their inter-relations.. Some of the consequences of this definition are discussed. It is shown that this definition encompasses several existing varieties of complexity measures and is then applied to some examples pertaining to the evolution of complex' systems including: "What is the complexity that has evolved in organisms and has it increased?". (shrink)