Reality: A Prerequisite to Meaningful Representation
Symbol grounding has been put forward as a candidate solution to the problem of associating intrinsic meaning obtained from sensorimotor data, to the arbitrary symbols that are so common in the cognitive domain. This paper focuses on the notion of how intrinsic meaning may be acquired and represented within an artificial cognitive system and considers how this task is influenced by varying the initial representations of sensory data and also the internal mechanics of the learning mechanism employed.
The task of ‘colour naming’ which involves grounding sensory representations of words (linguistic input) using sensory representations of colour (visual input), is described and it is shown, using a number of connectionist models, how the initial representation of colour effects the acquisition of the ‘colour naming’ ability. Results from the use of both psychologically based and other purely arbitrary representations lead to the conclusion that the representations used within cognitive architectures should possess structure that is lawfully related to the objects being represented, or alternatively representation must pay close attention to reality.
KeywordsSensory Representation Adaptive Resonance Theory Initial Representation Meaningful Representation Sensory Space
Unable to display preview. Download preview PDF.
- Berlin, B. & Kay, P. (1969) Basic Color Terms: Their Universality and Evolution. Berkeley, CA: University of California Press.Google Scholar
- Block, N. (1980) Troubles with functionalism. In: Block, N. (ed.) Readings in philosophy and psychology. Cambridge: Harvard.Google Scholar
- Dorffner, G. (1999) The Connectionist Route to Embodiment and Dynamicism. This volume.Google Scholar
- Lakoff, G. (1987) Women, Fire, and Dangerous Things; What Categories Reveal about the Mind. University of Chicago Press.Google Scholar
- Lammens, J. M. (1994) A Computational Model of Color Perception and Color Naming. Doctoral dissertation. State University of New York.Google Scholar
- Lyons, J. (1977) Semantics. Cambridge Univ. Press.Google Scholar
- McCloskey, M. & Cohen, N. (1980) Catastrophic interference in connectionist networks: The sequential learning problem. In: Bower, G. (ed.) The Psychology of Learning and Motivation. New York: Academic Press.Google Scholar
- McKevitt, P. (ed.) (1996) Integration of natural language and vision processing: Grounding representations. Artificial Intelligence Review 10(1–2).Google Scholar
- Rosch, E. (1978) Principles of categorisation In: Cognition and Categorisation. Hillsdale, NJ: Lawrence Erlbaum Associates.Google Scholar
- Williamson, J. R. (1995) GaussianARTMAP: A neural network for fast incremental learning of noisy multidimensional maps. Boston University, Dept. of Cognitive and Neural Systems. Technical Report CAS/CNS-95-003.Google Scholar
- Winograd, T. (1972) Understanding Natural Language. New York: Academic Press.Google Scholar