CiteSeerX — Concept Formation and Language Sharing: Combining Steels' Language Games with Simple Competitive Learning

Concept Formation and Language Sharing: Combining Steels' Language Games with Simple Competitive Learning (2002)

Popular Tags

No tags have been applied to this document.

BibTeX | Add To MetaCart

@MISC{Lewin02conceptformation,
    author = {Michael Lewin},
    title = {Concept Formation and Language Sharing: Combining Steels' Language Games with Simple Competitive Learning},
    year = {2002}
}

Bookmarks

OpenURL

Abstract:

Following on from the work of Luc Steels, this paper presents a model of Concept Formation and the subsequent use of Language Games to share those concepts in a society of artificial agents. The system is naturally driven towards stability due to two important mechanisms. In the Concept Formation stage, Simple Competitive Learning results in the formation of normative categories due to the identification of naturally occurring clusters of input data. In the Language Sharing stage, the preference for words that are frequently used creates a positive feedback loop towards linguistic coherence. The model can be seen as an extension to Steels' work because it makes an important generalisation. In Steels' model, all inputs are one-dimensional and categories are formed and refined by repeatedly bisecting the space. In this model the Input Space can have any dimension and is partitioned into categories of different shapes which are not fixed. The nature of the Input Space is deliberately very general - any number of dimensions and distribution of data can be specified. Consequently the model can be applied to any categorisation situation and is relevant to both scientific research and commercial applications. This paper begins by imitating the model used by Steels and then goes on to show the importance of a "forgetting mechanism" in order to improve communicative success. Higher dimensional spaces are then considered and the effect of various parameters on communicative success is examined. In particular, the importance of choosing the number of objects in the Language Game correctly is explained. Finally, agents' adaptability to a foreign environment is investigated by mixing two distinct populations.

Citations

874	The magical number seven, plus or minus two: Some limits on our capacity to process information – Miller - 1956
531	The symbol grounding problem – Harnad - 1990
309	Evolution and the Theory of Games – Smith - 1982
244	Minds, Brains and Programs – Searle - 1980
71	Emergent adaptive lexicons – Steels - 1996
58	The emergence of a ‘language’ in an evolving population of neural networks – Cangelosi, Parisi - 1998
58	Navigating with a rat brain: A neurobiologically-inspired model for robot spatial representation – Mataric - 1991
54	A Case Study in the Behavior-oriented Design of Autonomous Agents,’ From Animals to Animats – Steels - 1994
48	Evolving communication without dedicated communication channels – Quinn - 2001
45	Constructing and Sharing Perceptual Distinctions – Steels - 1997
34	The Adaptive Advantage of Symbolic Theft Over Sensorimotor Toil: Grounding Language in Perceptual Categories – Cangelosi, Harnad - 2001
34	Towards robot cooperation – McFarland - 1994
33	From robotic toil to symbolic theft: Grounding transfer from entry-level to higher-level categories. Connection Science 12:143–162. 18 The theory is part of a larger investigation of vision-language integration in AI, which also includes empirical work on – Cangelosi, Greco, et al.
31	Building Fungus Eaters: Design Principles of Autonomous Agents – Pfeifer - 1996
26	Learned Categorical Perception in Neural Nets: Implications for Symbol Grounding – Harnad, Hanson, et al. - 1994
24	Extracting regularities in space and time through a cascade of prediction networks – Nolfi, Tani - 1999
23	On simulating the evolution of communication – Noble, Cliff - 1996
19	Modular and hierarchical learning systems – Jordan, Jacobs - 1995
13	Symbol grounding and the symbolic theft hypothesis – Cangelosi, Greco, et al. - 2002
4	Computer simulation: A new scientific approach to the study of language evolution – Cangelosi, Parisi - 2002
4	Symbol grounding and the origin of language – Harnad - 2002
3	Category induction and representation. In: Categorical perception: The groundwork of cognition (S – Harnad - 1987
2	editors. Views into the Chinese Room – Bishop, Preston - 2002
2	A connectionist model of categorical perception and symbol grounding – Greco, Cangelosi - 1997
1	A neural network model for categorical perception and symbol grounding – Cangelosi, Greco, et al. - 1998
1	Induction, evolution and accountability. Origins and Evolution of Language and Speech – Harnad - 1976
1	Behavoural coordination in acoustically coupled agents – Paolo - 1998