UDC 681.3
EVOLUTIONARY METHOD OF CONSTRUCTING ARTIFICIAL INTELLIGENCE SYSTEMS
Abstract. The paper describes an evolutionary model for artificial intelligence construction, designed for the development of intelligent systems. It allows describing a variety of subject areas with the construction of knowledge bases. The model has universal means for formal description of tasks, as well as environment for implementing computational processes of their solution. The key element of the proposed model is a so-called ALF, which is an intelligent agent with the ability of learning, communication, self-organization, and joint action with other agents. The development of ALF agents is based on evolutionary principles implemented with the use of genetic algorithms. The implementation of the proposed approach was performed as a game model. A considerable flexibility and efficiency of the model demonstrated in the experiments are due to the unique structure and functionality of ALF agents.
Keywords: artificial intelligence, multi-agent systems, evolutionary programming.
FULL TEXT
REFERENCES
- Nirenburg S., Raskin V. Ontological semantics. Cambridge, MA: MIT Press. 2004. 440 p.
- Bratko I. Prolog programming for artificial intelligence. Harlow, England; New York: Addison Wesley, 2001. 678 p.
- Gardner M. Mathematical games — The fantastic combinations of John Conway’s new solitaire game “life”. Scientific American. 1970. Vol. 223. P. 120–123.
- Luger G.F. Artificial intelligence: Structures and strategies for complex problem solving (Russian translation). Moscow: Viliams, 2003. 864 p.
- Gould S.J. Full house: The spread of excellence from Plato to Darwin. New York: Harmony Books, 1996. 244 p.
- Von Neumann J., Burks A.W. Theory of self-reproducing automata. Urbana: University of Illinois Press, 1966. 418 p.
- Codd E.F. Cellular automata. Orlando: Academic Press, 1968. 132 p.
- Langton C.G. Studying artificial life with cellular automata. Physica D: Nonlinear Phenomena. 1986. Vol. 22, Issues 1–3. P. 120–149.
- Hightower R. The Devore universal computer constructor. Presentation at the Third Workshop of Artificial Life. Santa Fe, NM, 1992.
- Brooks R.A. Intelligence without reason. Proc. of the Twelfth International Joint Conference on Artificial Intelligence (IJCAI-91). Sydney, Australia. 1991. P. 569–595.
- Nilsson N. J. Teleo-reactive programs for agent control. Journal of Artificial Intelligence Research. 1993. Vol. 1, N 1. P.139–158,
- Crutchfield J.P., Mitchell M. The evolution of emergent computation.
Proc. of the National Academy of Sciences of the United States of America. 1995.
Vol. 92 (23). P. 10742-10746. DOI: https://doi.org/10.1073/pnas.92.23.10742