Neo: Learning conceptual knowledge by sensorimotor interaction with an environment

Paul R. Cohen, Marc S. Atkin, Tim Oates, Carole R. Beal

Research output: Contribution to conferencePaperpeer-review

21 Scopus citations

Abstract

Recent developments in philosophy, linguistics, developmental psychology and artificial intelligence make it possible to envision a developmental path for an artificial agent, grounded in activity-based sensorimotor representations. This paper describes how Neo, an artificial agent, learns concepts by interacting with its simulated environment. Relatively little prior structure is required to learn fairly accurate representation of objects, activities, locations and other aspects of Neo's experience. We show how classes (categories) can be abstracted from these representations, and discuss how our representation might be extended to express physical schemas, general, domain-independent activities that could be the building blocks of concept formation.

Original languageEnglish (US)
Pages170-177
Number of pages8
StatePublished - Jan 1 1997
EventProceedings of the 1997 1st International Conference on Autonomous Agents - Marina del Rey, CA, USA
Duration: Feb 5 1997Feb 8 1997

Other

OtherProceedings of the 1997 1st International Conference on Autonomous Agents
CityMarina del Rey, CA, USA
Period2/5/972/8/97

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Neo: Learning conceptual knowledge by sensorimotor interaction with an environment'. Together they form a unique fingerprint.

Cite this