軟性計算理論與知識處理技術之研究

On Soft Computing Theory and Knowledge Processing Technology

林信成(Sinn-Cheng Lin)

《教育資料與圖書館學》 38卷2期 (2000/12) Pp. 148-173

https://doi.org/10.6120/JoEMLS.200012_38(2).0004.RS.CM

並列摘要

Knowledge is the essential element of human thoughts. Creating an artificial system with knowledge and intelligence, furthermore, has been one of the humankind’s long-term visions. The computer has been the smartest machine ever since human history in technology began. Therefore, people attempted to use computer to realize human intelligence such as thinking, reasoning, learning. However, it always encountered numerous bottlenecks. The operating model of a computer is absolutely different from that in human brain. The computer is superior to human brain by its computing ability. But the computer loses its efficiency in conceptualizing, thinking, reasoning and distinguishing. The soft computing theory is developed to make a connection between machine intelligence and human brain. With such a theory, researchers on knowledge engineering can transfer the minding process, recognition structure and learning procedure of human into mathematical models. Then, they could work on any kinds of analysis, designing, simulation and experiments systematically. By doing so, the knowledge processing ability of artificial intelligent system can be improved and enhanced. This paper is focused on the integration issues of soft computing theory. It discusses the application potential of soft computing in the fields of machine thinking, machine recognizing, and machine learning. In addition, it also anatomizes the role of knowledge processing technologies that based on soft computing theory play in modem knowledge engineering.

並列關鍵字

Modern knowledge engineering ； Soft eomputing theory ； Knowledeg processing technology

參考文獻

Barto, A. G.,Sutton, R. S.,Anderson, C. W.(1983).Neuronlike Adaptive Elements That Can Solve Difficult Learning Control Problems.IEEE Trans. on Syst. Man and Cyber.13(5),834-846.

Berenji, H. R.,Khedkar, P.(1992).Learning and Turning Fuzzy Logic Controllers through Reinforcements.IEEE Trans. on Neural Net.3(5),724-740.

De Jong, K. A.(1980).Adaptive System Design: A genetic approach.IEEE Trans. on Syst. Man and Cyber.10(9),566-574.

De Jong, K. A.(1987).Genetic Algorithms and Their Applications: Proc. of 2'nd Int. Conf. on Genetic Algorithms.

Folger, T. A.(1988).Fuzzy Sets, Uncertainty, and Information.