Cogprints

The Symbol Grounding Problem

Harnad, Stevan (1990) The Symbol Grounding Problem. [Journal (Paginated)]

Warning

There is a more recent version of this eprint available. Click here to view it.

Full text available as:

[img]HTML
54Kb

Abstract

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 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.

Item Type:Journal (Paginated)
Keywords:computation, cognition, semantics, robotics, Turing Test, Chinese Room Argument, symbol grounding, categorisation, consciousness, situatedness, embodiment, transduction, sensorimotor processes, artificial intelligence, hermeneutics, neural nets
Subjects:Biology > Theoretical Biology
Psychology > Cognitive Psychology
Neuroscience > Computational Neuroscience
Computer Science > Artificial Intelligence
Computer Science > Dynamical Systems
Computer Science > Neural Nets
Computer Science > Robotics
Linguistics > Semantics
Psychology > Perceptual Cognitive Psychology
Philosophy > Epistemology
Philosophy > Philosophy of Language
ID Code:615
Deposited By:Harnad, Stevan
Deposited On:20 Mar 1998
Last Modified:11 Mar 2011 08:54

Available Versions of this Item

Metadata

Repository Staff Only: item control page