Model-Based Testing and Evaluation on ArtificialIntelligence Systems
In this paper, we discuss how viewing a Artificial Intelligence system as a model leads to certain criteria for testing methodologies. This includes a discussion of how certain mathematical techniques for testing Artificial Intelligence systems can be used as criteria for Artificial Intelligence system adequacy when no other models are available. We give an example of an error due to widespread rule interactions. Such errors are keys to understanding why the independent rule assumption does not work, and therefore why Artificial Intelligence systems must be modeled. We examine how testing can be applied both to individual system components as well as the system as a whole, different criteria by which a set of test cases can be assembled and the problems in determining whether the performance of a Artificial Intelligence systems on a set of test cases is acceptable.
AI Systems Testing Model
Gang Liu Qun Liu Peng Xie
the College of Computer Science and Technology, Harbin Engineering University, Harbin, Heilongjiang, CO 150001 China
国际会议
武汉
英文
2007-09-21（万方平台首次上网日期，不代表论文的发表时间）