计算机英语第五章.ppt

人工智能是一门极富挑战性的科学，它由不同的领域组成，如数学、统计学、数据挖掘、机器学习等。人工智能研究的一个主要目标是使机器能够胜任一些通常需要人类智能才能完成的复杂工作。人工智能的发展历史是和计算机科学与技术的发展史联系在一起的。人工智能学科研究的主要内容包括：知识表示、自动推理和搜索方法、机器学习和知识获取、知识处理系统、自然语言理解、计算机视觉、智能机器人、自动程序设计等方面。实际应用包括机器视觉、指纹识别、人脸识别、视网膜识别、掌纹识别、专家系统、智能搜索、定理证明、博弈、自动程序设计等。研究范畴包括自然语言处理、知识表现、推理、规划、机器学习、知识获取、组合调度、感知、模式识别、逻辑程序设计、软计算等。 本章难句、长句较多，读者在学习本章内容时，可以参考给出的部分译文辅助理解。 This approach largely overcomes many problems of the probabilistic reasoning systems of the 1960s and 1970s; and it now dominates AI research on uncertain reasoning and expert systems. The approach allows for learning from experience, and it combines the best of classical AI and neural nets. Work by Judea Pearl and by Eric Horvitz and David Heckerman promoted the idea of normative[1] expert systems: ones that act rationally according to the laws of decision theory and do not try to imitate the thought steps of human experts. The windows operating system includes several normative diagnostic expert systems for correcting problems. [1] normative: adj. 标准的, 规范的 Similar gentle[1] revolutions have occurred in robotics, computer vision, and knowledge representation. A better understanding of the problems and their complexity properties, combined with increased mathematical sophistication, has led to workable research agendas[2] and robust methods. [1] gentle: adj. 温和的 [2] agenda: n. 议程 In many cases, formalization [1] and specialization have also led to fragmentation [2] : topics such as vision and robotics are increasingly isolated from mainstream AI work. The unifying[3] view of AI as rational agent design is one that can bring unity back to these disparate fields[i]. [1] formalization: n. 形式化 [2] fragmentation: n. 分裂 [3] unifying: adj. 一致的, 一体化的 [i] 把人工智能视为理性智能体设计的整体的观点，是一种可以重新给这些全异的领域带来统一的观点。disparate：全异的。  (6) The emergence of intelligent agents (1995-present) Perhaps encouraged by the progress in solving the subproblems of AI[i] , researchers have also started to look at the whole agent problem again. The w