第1章 人工智能导论.pptVIP

Questions Can machines think? If so, how? If not, why not? 第1章 人工智能概述 1.1 什么是人工智能 1.2 人工智能的研究意义、目标和策略 1.3 人工智能的学科范畴 1.4 人工智能的研究内容 1.5 人工智能的研究途径与方法 1.6 人工智能的基本技术 1.7 人工智能的应用 1.8 人工智能的分支领域与研究方向 1.9 智能计算机技术 1.1 什么是人工智能 ◆人工智能（Artificial Intelligence”，AI） 1.1.1 人工智能概念的一般描述 ◆部分学者对人工智能概念的描述： —— 人工智能是那些与人的思维相关的活动，诸如决策、问题求解和学习等的自动化（Bellman, 1978）； —— 人工智能是一种计算机能够思维，使机器具有智力的激动人心的新尝试（Haugeland, 1985）； ——人工智能是研究如何让计算机做现阶段只有人才能做得好的事情（Rich Knight,1991）； —— 人工智能是那些使知觉、推理和行为成为可能的计算的研究（Winston, 1992）； —— 广义地讲，人工智能是关于人造物的智能行为，而智能行为包括知觉、推理、学习、交流和在复杂环境中的行为（Nilsson，1998）。 —— Stuart Russell和Peter Norvig把已有的一些人工智能定义分为4类：像人一样思考的系统、像人一样行动的系统、理性思考的系统、理性行动的系统（2003）。 What is AI? Q. What is intelligence? A. Intelligence is the computational part of the ability to achieve goals in the world. Varying kinds and degrees of intelligence occur in people, many animals and some machines. Q. What is artificial intelligence? A. It is the science and engineering of making intelligent machines, especially intelligent computer programs. It is related to the similar task of using computers to understand human intelligence. 智能机器 智能机器 布尔逻辑 About Turing Test Three rooms contain a person, a computer, and an interrogator(测试者). The interrogator can communicate with the other two by teleprinter. The interrogator tries to determine which is the person and which is the machine. The machine tries to fool the interrogator into believing that it is the person. If the machine succeeds, then we conclude that the machine can think. Turing Test What’s easy and what’s hard? It’s been easier to mechanize (机械化) many of the high-level tasks we usually associate with “intelligence” in people e.g., symbolic integration, proving theorems, playing chess, medical diagnosis It’s been very hard to mechanize tasks that lots of animals can do walking around without running into things catching prey(被捕食动物) and avoidin