《不确定性人工智能》.pdf

1000-9825/2004/15(11)1583 © 2004 Journal of Software 软 件 学 报 Vol.15, No.11 不确定性人工智能 1+ 2 3 2 李德毅 , 刘常昱 , 杜 鹢 , 韩 旭 1( 中国电子工程系统研究所,北京 100840) 2 ( 中国人民解放军理工大学,江苏 南京 210007) 3( 中国电子设备系统工程公司,北京 100840) Artificial Intelligence with Uncertainty 1+ 2 3 2 LI De-Yi , LIU Chang-Yu , DU Yi , HAN Xu 1(China Institute of Electronic System Engineering, Beijing 100840, China) 2(PLA University of Science and Technology, Nanjing 210007, China) 3(China Electronic System Engineering Company, Beijing 100840, China) + Corresponding author: E-mail: ziqin@, /ldy/index_ldy.asp Received 2004-07-13; Accepted 2004-09-13 Li DY, Liu CY, Du Y, Han X. Artificial intelligence with uncertainty. Journal of Software, 2004,15(11): 1583~1594. /1000-9825/15/ 1583.htm Abstract: Uncertainty exists widely in the subjective and objective world. In all kinds of uncertainty, randomness and fuzziness are the most important and fundamental. In this paper, the relationship between randomness and fuzziness is discussed. Uncertain states and their changes can be measured by entropy and hyper-entropy respectively. Tak en advantage of entropy and hyper-entropy, the uncertainty of chaos, fractal and complex networks by their various evolution and differentiation are further studied. A simple and effective way is proposed to simulate the uncertainty by means of knowledge representation which provides a basis for the automation of both logic and image thinking with uncertainty. The AI (artificial intelligence) with uncertainty is a new cross-discipline, which covers computer science, physics, mathematics, brain science, psychology, cognitive science, biology and philosophy, and results in the automation of representation, proce