Beyond the Turing Test: Performance Metrics for Evaluating a Computer Simulation of the Human Mind
ICDL '02 Proceedings of the 2nd International Conference on Development and Learning(2002)
摘要
Performance metrics for machine intelligence (e.g.,theTuring test) have traditionally consisted of pass/fail tests.Because the tests devised by psychologists have been aimedat revealing unobservable processes of human cognition,they are similarly capable of revealing how a computeraccomplishes a task, not simply its success or failure.Herewe adapt a set of tests of abilities previously measured inhumans to be used as a benchmark for simulation of humancognition.Our premise is that if a machine cannot passthese tests, it is unlikely to be able to engage in the morecomplex cognition routinely exhibited by animals andhumans.If it cannot pass these tests, it will lackfundamental capabilities underlying such performance.
更多查看译文
关键词
aimedat revealing unobservable process,Computer Simulation,human cognition,machine intelligence,Human Mind,morecomplex cognition,animals andhumans,Performance Metrics,Turing Test,theTuring test,performance metrics,passthese test
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络