计算之智与哲学之慧分享 http://blog.sciencenet.cn/u/huangfuqiang

博文

语义理解是机器自我学习的困难之所在101006

已有 4956 次阅读 2010-10-6 10:36 |个人分类:数据挖掘与机器学习|系统分类:科研笔记

               人机象棋大战、预测天气等科技事实给人造成机器优于人类的假象,然而机器对各种信息源的组合能力远远不如人类。这其中很重要的方面就是人类可以对错综复杂的语义进行认知处理,人类具有很强的上下文(语境)结合能力和自由利用背景知识的能力,机器智能在这两个方面是比较弱的,尽管已经取得了一些进展。今年初,CMU 的一个研究团队开始着力于研究通过语义学习来提高机器的认知水平,缩短与人类智能的距离,这要以超级计算设施作为运行基础的。算法与计算能力消耗的均衡考虑,或许可以降低计算能量的消耗,慢慢缩小计算控制与执行部分的体积。这方面不能故意吹得神奇,想要克服的问题非常多。但我认为基于语义的智能研究是机器学习、智能决策支持研究等方面的生长点。下面是CMU研究团队教授讲的一句话:
       “For all the advances in computer science, we still don’t have a computer that can learn as humans do, cumulatively, over the long term,” said the team’s leader, Tom M. Mitchell, a computer scientist and chairman of the machine learning department.
        这个小组的工程简介:Read  the Web
NELL: Never-Ending Language Learning
         Can computers learn to read? We think so. "Read the Web" is a research project that attempts to create a computer system that learns over time to read the web. Since January 2010, our computer system called NELL (Never-Ending Language Learner) has been running continuously, attempting to perform two tasks each day:
        First, it attempts to "read," or extract facts from text found in hundreds of millions of web pages (e.g., playsInstrument(George_Harrison, guitar)).
        Second, it attempts to improve its reading competence, so that tomorrow it can extract more facts from the web, more accurately.
        学术工程研究主页

Aiming to Learn as We Do, a Machine Teaches Itself



http://blog.sciencenet.cn/blog-89075-370143.html

上一篇:NoSQL简介101002
下一篇:亚洲编程语言与系统专题研讨会(APLAS2010)

2 陶依红 yinglu

该博文允许实名用户评论 评论 (1 个评论)

数据加载中...

Archiver|手机版|科学网 ( 京ICP备07017567号-12 )

GMT+8, 2020-10-21 18:24

Powered by ScienceNet.cn

Copyright © 2007- 中国科学报社

返回顶部