DOI QR코드

DOI QR Code

Semantic Aspects of Negation as Schema

부정 스키마의 의미론적 양상

  • Tae, Kang-Soo (Dept.of Information Technology Computer Engineering, Jeonju University)
  • 태강수 (전주대학교 정보기술컴퓨터공학부)
  • Published : 2002.02.01

Abstract

A fundamental problem in building an intelligent agent is that an agent does not understand the meaning of its perception or its action. One reason that an agent cannot understand the world is partially caused by a syntactic approach that converts a semantic feature into a simple string. To solve this problem, Cohen introduces a semantic approach that an agent autonomously learns a meaningful representation of physical schemas, on which some advanced conceptual structures are built, from physically interacting with environment using its own sensors and effectors. However, Cohen does not deal with a meta level of conceptual primitive that makes recognizing a schema possible. We propose that negation is a meta schema that enables an agent to recognize a physical schema. We prove some semantic aspects of negation.

지능형 에이전트를 구현하는데 있어서 하나의 근본적인 문제는 에이전트가 자신의 인식이나 행동의 의미를 이해하지 못한다는 점이다. 에이전트가 세계를 이해하지 못하는 이유중의 하나는 의미론적 자질을 단순한 문자열로 변환시키는 구문론적 접근방법에서 야기한다. 이 문제를 해결하기 위해 코헨은 에이전트가 자율적으로 자신의 센서와 행동자를 사용하여 환경과 상호작용 함으로써 고급 개념의 기초가 되는 물리적 스키마를 배우는 의미론적 방법을 소개한다. 하지만 코헨은 스키마를 이해하는 것을 가능하게 해주는 상위 계층의 개념소자는 다루지 않는다. 본 논문에서는 부정은 물리적 스키마의 인식을 가능하게 해주는 메타 스키마라는 제안을 하고 부정의 몇 가지 의미론적 양상들을 증명한다.

Keywords

References

  1. Allen, J., Hendler, J., and Tate, A., Readings in Machine Planning, Morgan KaufMann Publishers, 1990
  2. Brum, A. L. and Furst, M. L., Fast Planning through Planning Graph Analysis, Artificial Intelligence 90(1-2) : 281-300, 1997 https://doi.org/10.1016/S0004-3702(96)00047-1
  3. Carbonell, J. G., Blythe, J., Etzioni, O., Gil, Y., Knoblock, C., Minton, S., Perez, A., and Wang, X. PRODIGY 4.0: The Manual and Tutorial, Technical Report CMU-CS-92-150, Carnegie Mellon University, Pittsburgh, PA, 1992
  4. Cohen, P. R., Atkin, M. S., Oates, T., Neo : Learning Conceptual Knowledge by Sensorimotor Interaction with an Environment, Proceedings of the 6th International Conference on Intelligent Autonomous System, 2000
  5. Cohen, P. R. Learning Concepts by Interaction, Proceedings of the 6th International Conference on Intelligent Autonomous System, 2000
  6. Cohen, P. R., Oates, T., Adams, N., Beal, C. R., Robot Baby 2001, Invited Talk at 12th International Conference on Algorithmic Learning Theory, 2001
  7. Fikes, R. and Nilsson, N. STRIPS : A New Approach to the Application of Theorem Proving to Problem Solving, in Artificial Intelligence, 2, 1971 https://doi.org/10.1016/0004-3702(71)90010-5
  8. Kaelbling, L. P., Oates, T., Hernandes, N., and Finney, S., Leaming in Worlds with Objects, 2001 AAAI Spring Symposium Workshop, Stanford University, 2001
  9. Koehler, J. Extending Planning Graphs to an ADL Subset, Proc. 4th European Conference on Planning, 1997
  10. Mandler, J. M., How to build a baby: Conceptual primitives, Psychological Review, 99(4), 1992
  11. McCarthy, J., Situations, atcions, and causal laws, Stanford Artificial intelligence Project : Memo 2, 1963
  12. Quinlan, J. R., C4.5 : Programs for Machine Learning, Morgan Kaufmann, 1993
  13. Russell, S. Norvig, P., Artificial Intelligence: A Modem Approach, Prentice-Hall International, 1995
  14. Searle, J. R., Minds, Brains, and Programs, Behavioral and Brain Science, 1980
  15. Shavlik, J. W., and Dietterich, T. G., Readings in Machine Learning, Morgan KaufMann Publishers, 1990
  16. Tae, K. S., Cook, D. and Holder, L. B. Experimentation-Driven Knowledge Acquisition for Planning, Computational Intelligence, 15(3), 1999 https://doi.org/10.1111/0824-7935.00093
  17. 태강수, '에이전트의 부정에 대한 학습', 정보과회논문지: 소프트웨어 및 응용, 27(5), 2000
  18. Wittgenstein, L., Philosophical Investigations, Macmillan, London, 1953