MIT的《深度学习》精读（9）

Several artificial intelligence projects have sought to hard-code knowledge about the world in formal languages. A computer can reason about statements in these formal languages automatically using logical inference rules. This is known as the knowledge base approach to artificial intelligence. None of these projects has led to a major success. One of the most famous such projects is Cyc (Lenat and Guha,
1989). Cyc is an inference engine and a database of statements in a language called CycL. These statements are entered by a staff of human supervisors. It is an unwieldy process. People struggle to devise formal rules with enough complexity to accurately describe the world. For example, Cyc failed to understand a story about a person named Fred shaving in the morning (Linde, 1992). Its inference engine detected an inconsistency in the story: it knew that people do not have electrical parts, but because Fred was holding an electric razor, it believed the entity “FredWhileShaving” contained electrical parts. It therefore asked whether Fred was still a person while he was shaving. 

有好几个人工智能的项目都试图使用普通的编程的方式，硬编码地把全世界的知识输入到计算机里，以便计算机可以自动从那些逻辑规则来产生智能的推理。用这种方式来构造人工智能的过程叫做知识库的方法，但是这些项目没有一个取得重大的成功。其中最出色的要算Cyc(Lenat and Guha,1989)项目了，它是一个逻辑推理的引擎，采用一种叫做CycL语言来编写推理规则的知识数据库，这些规则语句都是由人工的方式进行输入去。这是一个非常笨拙的过程，因为人们很难设计出足够复杂的规则来准确地描述这个现实世界。例如，Cyc在尝试理解Fred在早上刷胡子的故事时就出错了(Linde, 1992)，在这个故事里，Cyc的推断引擎就前后矛盾，它知道人是没有电器部分的，但当有一个叫Fred的人手里拿着一个电动胡须刀时，它却认为“FredWhileShaving”当作一个整体，因此当Fred拿着胡须刀时，它却在问Fred是否还是一个人。

The Syntax of CycL

CycL is a formal language whose syntax derives from first-order predicate calculus (the language of formal logic) and from Lisp. In order to express common sense knowledge, however, it goes far beyond first order logic. The vocabulary of CycL consists of terms. The set of terms can be divided into constants, non-atomic terms (NATs), variables, and a few other types of objects. Terms are combined into meaningful CycL expressions, which are used to make assertions in the CYC knowledge base.

This document will be sloppy with respect to the distinction between the formal language CycL and the datastructures used to represent CycL expressions in the CYC KB. Of course these are two separate things, but for explanatory purposes it is useful to overload the vocabulary.

• Constants
• Variables
• Sentences
• Predicates
• Logical Connectives
• Quantification
• Non-Atomic Terms
• Assertions

1. TensorFlow API攻略

http://edu.csdn.net/course/detail/4495

2. TensorFlow入门基本教程

http://edu.csdn.net/course/detail/4369

3. C++标准模板库从入门到精通 

http://edu.csdn.net/course/detail/3324

4.跟老菜鸟学C++

http://edu.csdn.net/course/detail/2901

5. 跟老菜鸟学python

http://edu.csdn.net/course/detail/2592

6. 在VC2015里学会使用tinyxml库

http://edu.csdn.net/course/detail/2590

7. 在Windows下SVN的版本管理与实战 

 http://edu.csdn.net/course/detail/2579

8.Visual Studio 2015开发C++程序的基本使用 

http://edu.csdn.net/course/detail/2570

9.在VC2015里使用protobuf协议

http://edu.csdn.net/course/detail/2582

10.在VC2015里学会使用MySQL数据库

http://edu.csdn.net/course/detail/2672