- 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
- 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载。
- 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
- 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
- 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们。
- 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
- 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
具体概念表示为模式自动机
Concrete Concept Represented as Automaton of Pattern
Abstract: We use general pattern and automaton of it to represent concrete concept. And give a new concept of “information hardness and hardness degree”. An automaton of pattern can be realized with local search with two strategies: “deviation of Yellow River” and “excite /depress”. Learning is building possible pattern relations and searching pattern satisfies phenomena. “Larger pattern is prior” is the principle of dialectic logic, it can avoid “over learn” and develop more complicated patterns.We have conditioned law of excluded middle, like: ~M(x) →H(x)∨~H(x); H(x)~H(x)→M(x).
Keywords: Artificial intelligence, concept, dialectic logic, pattern, agent.
摘要: 我们使用模式及模式上的自动机表示具体概念。给出“信息硬度和信息硬度级”概念。用局域搜索和“黄河改道”、“兴奋/抑制” 策略,可实现模式自动机的运动。学习成为构造和搜索满足现象的模式过程。“大模式优先”是辩证逻辑原则,可避免“过渡学习”并发展更复杂概念。我们给出条件排中律,如:~M(x) →H(x)∨~H(x); H(x)~H(x)→M(x)。
关键词: 人工智能,概念,辩证逻辑,模式,主体
A lot of represent method of AI have been developed. The concrete concept is the concept studied by dialectic logic. We want develop a general represent system of concrete concept. And give its form, its move -- reason and its build -- learning. This is the basic part of a methodology for AI of dialectic logic.
Automaton of pattern, information hardness
What is concept and how it works? In Buddhism there is a definition of “dharma”, it means object, in the mind or in the world. The definition says that dharma keeps properties and has law, by the properties and by the law we can recognize and understand it. The definition, name, law of concept and relations of them are patterns.
Pattern can be represented as:
f(x1, x2, ..., xn).
Here f is the pattern relation and x1, x2, …, xn are factors in the pattern. Patterns can be nested and items can be shared. So information transfers through them.
Pattern is general. It may be proposition, mathematic relation, neural network, or sentence that f as verb, and so on.
The system is open. So
原创力文档


文档评论(0)