Algorithmic research on computational learning and teaching
Algorithmic research on computational learning and teaching
批准号:
02680031
负责人:
MIYANO Satoru
金额:
$1.15万
依托单位:
依托单位国家:
日本
项目类别:
Grant-in-Aid for General Scientific Research (C)
财政年份:
1990
资助国家:
日本
项目状态:
已结题
起止时间:
1990 至 1991
中文摘要
本研究从算法教学的角度对计算学习进行了研究。我们引入了可教性的概念,用它来建立可学性和可教性之间的关系。我们在教师与学习有关的复杂性问题上得到了一些结果。我们还考虑了与学习有关的类比推理。我们证明了在类比推理中出现了NP-难方面。在我们的框架中,集合覆盖问题被证明是教学中寻找关键字的一个重要问题。针对这个问题,我们设计了一个并行算法来解决最小集覆盖问题。我们还研究了关于多项式时间可学习性的初等形式系统。我们确定了初等形式系统的一些重要和有用的子类,它们是多项式时间可学习的。在这些理论研究的基础上,我们开发了一个基于规则模式的决策树机器学习系统。该系统从随机选择的样本中找出重要的密钥,可以合理地解释给定的样本。除了对我们的系统进行理论分析外,实验表明,该机器学习系统取得了相当成功的结果。为了在教学中寻找关键问题,我们还开发了一个基于初等形式系统的系统,该系统采用了最小集合覆盖问题的近似算法。两种系统的比较表明,前者比后者更快、更高效。但是,由于理论上的原因,后一种制度可以应对种类更多的问题。
英文摘要
This research concentrates on computational learning from the view point of algorithmic teaching. We introduced the notion of teachability with which we established a relationship between the learnability and teachability. We obtained some results on the complexity issues of a teacher in relation to learning. We also considered the analogical reasoning in relation to learning. We showed that NP-hard aspect appears in analogicaj reasoning. In our framework, the set cover problem proved to be an important issue for finding keys in teaching. For this problem we devised a parallel algorithm which solves the minimal set cover problem. We also investigated elementary formal systems with respect to polynomial-time learnability. We identified some important and useful subclasses of elementary formal systems which are polynomial-time learnable. Based on these theoretical researches, we developed a machine learning system which employs decision trees over regular patterns. This system finds important keys from randomly chosen samples which may explain the given samples reasonably. In addition to theoretical analysis of our system, experiments show that this machine learning system exhibited quite successful results. In order to find keys in teaching, we also developed a system based on elementary formal systems which employs the approximation algorithm for minimum set cover problem. Comparison of these two systems showed that the former is faster and efficient than the latter. But, by theoretical reasons, the latter system can cope with problems with larger variety.
期刊论文(23)
专著(0)
科研奖励(0)
会议论文
登录
查看更多内容
Satoru Miyano: "Which classes of elementary formal systems are polynomial-time learnable?" Proc.2nd Workshop on Algorithmic Learning Theory. 139-150 (1991)
Satoru Miyano:“哪些类基本形式系统是多项式时间可学习的?”
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
A. Shinohara and S. Miyano: "Teachability in computational learning" New Generation Computing. 8. 337-347 (1991)
A. Shinohara 和 S. Miyano:“计算学习的可教性”新一代计算。
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
S. Miyano, A. Shinohara and T. Shinohara: "Which classes of elementary formal systems are polynomialtime learnable?" Proc. 2nd Workshop on Algorithmic Learning Theory. 139-150 (1991)
S. Miyano、A. Shinohara 和 T. Shinohara:“哪些基本形式系统可以用多项式时间学习?”
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
Setsuo Arikawa: "A learning algorithm for elementary formal systems and its experiments on identification of transmembrane domains" Proc.25nd Hawaii International Conference onf System Sciences. 1. 675-684 (1992)
Setsuo Arikawa:“基本形式系统的学习算法及其跨膜域识别实验”Proc.25nd 夏威夷系统科学国际会议。
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
S. Arikawa, S. Kuhara, S. Miyano: "A. Shinohara and T. Shinohara, A learning algorithm for elementary formal systems and its experiments on identification of transmembrane domains" Proc. 25th Hawaii International Conference on System Sciences. I. 675-684
S. Arikawa、S. Kuhara、S. Miyano:“A. Shinohara 和 T. Shinohara,基本形式系统的学习算法及其跨膜域识别实验”Proc。
DOI:
--
发表时间:
期刊:
影响因子:
--
作者:
[]
通讯作者:
共 23 条
Drug-response pathway analysis methods based on network analysis
-
批准号:22300099
-
项目类别:Grant-in-Aid for Scientific Research (B)
-
资助金额:$5.57万
-
财政年份:2010
-
负责人:MIYANO Satoru
-
依托单位:
In Silico Search for Drug Target Pathways by Gene Networks
-
批准号:18300097
-
项目类别:Grant-in-Aid for Scientific Research (B)
-
资助金额:$11.33万
-
财政年份:2006
-
负责人:MIYANO Satoru
-
依托单位:
Estimation and simulation of gene networks for developing in silico biological networks
-
批准号:17017008
-
项目类别:Grant-in-Aid for Scientific Research on Priority Areas
-
资助金额:$59.84万
-
财政年份:2005
-
负责人:MIYANO Satoru
-
依托单位:
Information Scientific Foundations of Knowledge Discovery from Proteome Data
-
批准号:15300099
-
项目类别:Grant-in-Aid for Scientific Research (B)
-
资助金额:$10.56万
-
财政年份:2003
-
负责人:MIYANO Satoru
-
依托单位:
Information Technoloy for Gene Network Analysis
-
批准号:15014205
-
项目类别:Grant-in-Aid for Scientific Research on Priority Areas
-
资助金额:$20.48万
-
财政年份:2003
-
负责人:MIYANO Satoru
-
依托单位:
Foundations of Computational Knowledge Discovery from cDNA Microarray Data
-
批准号:12480080
-
项目类别:Grant-in-Aid for Scientific Research (B)
-
资助金额:$9.22万
-
财政年份:2000
-
负责人:MIYANO Satoru
-
依托单位:
Knowledge Discovery in Databases
-
批准号:10143102
-
项目类别:Grant-in-Aid for Scientific Research on Priority Areas (A)
-
资助金额:$76.67万
-
财政年份:1998
-
负责人:MIYANO Satoru
-
依托单位:
Development of Data Mining System Using Binary Decision Diagrams for Knowledge Representation
-
批准号:09558032
-
项目类别:Grant-in-Aid for Scientific Research (B)
-
资助金额:$8.19万
-
财政年份:1997
-
负责人:MIYANO Satoru
-
依托单位:
Development of Parallel Knowledge Acquisition System
-
批准号:06558047
-
项目类别:Grant-in-Aid for Scientific Research (A)
-
资助金额:$11.07万
-
财政年份:1994
-
负责人:MIYANO Satoru
-
依托单位:
STUDY ON EFFICIENT SEARCH ALGORITHMS
-
批准号:06680326
-
项目类别:Grant-in-Aid for General Scientific Research (C)
-
资助金额:$1.41万
-
财政年份:1994
-
负责人:MIYANO Satoru
-
依托单位:
海外基金