Features of Machine Learning and Other Topics in Foundations of Computing
机器学习的特征和计算基础中的其他主题
基本信息
- 批准号:9020079
- 负责人:
- 金额:$ 18.79万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:1991
- 资助国家:美国
- 起止时间:1991-04-15 至 1993-09-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
This project will contribute toward the goal of understanding how a computer can be programmed to learn by isolating features of incremental learning algorithms that theoretically enhance their learning potential. The features are chosen to resemble features of human learning. For example, learning devices that use the results of one learning episode to aid in the next learning endeavor will be considered. Another powerful learning technique, for both humans and machines, is the ability to ask questions. Investigations into the relative learning potential of algorithms as the language they use to pose questions will be conducted. Preliminary results indicate that the more powerful the query language used, the greater the learning potential of the device asking questions. Parameters of query language strength such as the number of quantifiers and the number of alternations of quantifiers will be vigorously examined. Current program testing techniques do not and cannot determine correctness precisely. The purpose of these techniques is to reveal errors in a program; however, if no errors are found, no measure is given as to how reliable the program is. Therefore there is no notion of how "close" to correct the tested program is. The goal of this research is to develop a theory whereby it is possible to say precisely how reliable a program is when it passes a given test.
该项目将有助于理解计算机如何通过隔离增量学习算法的特征来编程学习,从而在理论上增强其学习潜力。这些特征被选择为类似于人类学习的特征。例如,使用一个学习事件的结果来帮助下一个学习努力的学习设备将被考虑。对人类和机器来说,另一种强大的学习技巧是提问的能力。将调查算法的相对学习潜力,作为它们用来提出问题的语言。初步结果表明,查询语言越强大,提问设备的学习潜力越大。查询语言强度的参数,如量词的数量和量词的变化数量将被严格检查。当前的程序测试技术不能也不能精确地确定正确性。这些技术的目的是揭示程序中的错误;但是,如果没有发现错误,则无法衡量程序的可靠性。因此,不存在如何“接近”纠正被测试程序的概念。这项研究的目的是发展一种理论,据此,当一个程序通过给定的测试时,就有可能准确地说出它的可靠性。
项目成果
期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
数据更新时间:{{ journalArticles.updateTime }}
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
Carl Smith其他文献
THE COST OF SEXUAL SIGNALING IN YEAST
酵母中性信号的成本
- DOI:
10.1111/j.1558-5646.2010.01069.x - 发表时间:
2010 - 期刊:
- 影响因子:3.3
- 作者:
Carl Smith;D. Greig - 通讯作者:
D. Greig
Genetic analysis of male reproductive success in relation to density in the zebrafish, Danio rerio
斑马鱼雄性繁殖成功率与密度的遗传分析
- DOI:
- 发表时间:
2006 - 期刊:
- 影响因子:2.8
- 作者:
R. Spence;W. Jordan;Carl Smith - 通讯作者:
Carl Smith
An Overview of Capturing Live Experience with Virtual and Augmented Reality
使用虚拟和增强现实捕捉现场体验概述
- DOI:
10.3233/978-1-61499-530-2-298 - 发表时间:
2015 - 期刊:
- 影响因子:0
- 作者:
Mikhail Fominykh;Fridolin Wild;Carl Smith;Victor Alvarez;M. Morozov - 通讯作者:
M. Morozov
Filial Cannibalism as a Reproductive Strategy in Care-Giving Teleosts?
孝顺同类相食是照顾硬骨鱼的一种繁殖策略?
- DOI:
10.1163/156854292x00107 - 发表时间:
1991 - 期刊:
- 影响因子:0
- 作者:
Carl Smith - 通讯作者:
Carl Smith
Chinese Christians: Elites, Middlemen, and the Church in Hong Kong
中国基督徒:精英、中间人和香港教会
- DOI:
10.2307/1870030 - 发表时间:
1985 - 期刊:
- 影响因子:0
- 作者:
Carl Smith - 通讯作者:
Carl Smith
Carl Smith的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('Carl Smith', 18)}}的其他基金
SBIR Phase II: Eddy Current Condition Monitoring of Metallic Flaws Under Surface Coatings Using Giant Magnetoresistance (GMR) Sensors
SBIR 第二阶段:使用巨磁阻 (GMR) 传感器对表面涂层下的金属缺陷进行涡流状态监测
- 批准号:
0216200 - 财政年份:2002
- 资助金额:
$ 18.79万 - 项目类别:
Standard Grant
SBIR Phase I: Eddy Current Condition Monitoring of Metallic Flaws Under Surface Coatings Using Giant Magnetoresistance (GMR) Sensors
SBIR 第一阶段:使用巨磁阻 (GMR) 传感器对表面涂层下的金属缺陷进行涡流状态监测
- 批准号:
0060447 - 财政年份:2001
- 资助金额:
$ 18.79万 - 项目类别:
Standard Grant
The Capabilities and Limitations of Atomated Discovery
自动化发现的能力和局限性
- 批准号:
9732692 - 财政年份:1998
- 资助金额:
$ 18.79万 - 项目类别:
Standard Grant
Cooperative US-Latvia Research in Inductive Inference
美国-拉脱维亚归纳推理合作研究
- 批准号:
9119540 - 财政年份:1992
- 资助金额:
$ 18.79万 - 项目类别:
Standard Grant
Capitol Area Theory Seminar: University of Maryland, College Park, Fall 1991 - Spring 1994
国会大厦地区理论研讨会:马里兰大学学院公园分校,1991 年秋季 - 1994 年春季
- 批准号:
9112976 - 财政年份:1991
- 资助金额:
$ 18.79万 - 项目类别:
Standard Grant
Inductive Inference and other topics in the Foundations of Computing (Computer and Information Science)
归纳推理和计算基础中的其他主题(计算机和信息科学)
- 批准号:
8701104 - 财政年份:1987
- 资助金额:
$ 18.79万 - 项目类别:
Continuing Grant
A Special Year for Logic and Related Aspects of Computer Science at the University of Maryland - College Park, 1984 - 1985
马里兰大学帕克分校逻辑和计算机科学相关方面的特殊一年,1984 年 - 1985 年
- 批准号:
8413498 - 财政年份:1984
- 资助金额:
$ 18.79万 - 项目类别:
Standard Grant
相似国自然基金
Understanding structural evolution of galaxies with machine learning
- 批准号:n/a
- 批准年份:2022
- 资助金额:10.0 万元
- 项目类别:省市级项目
相似海外基金
A machine learning model to assess the presence and severity of knee osteoarthritis based on gait data features
基于步态数据特征评估膝骨关节炎的存在和严重程度的机器学习模型
- 批准号:
23K16611 - 财政年份:2023
- 资助金额:
$ 18.79万 - 项目类别:
Grant-in-Aid for Early-Career Scientists
Leveraging evolutionary analyses and machine learning to discover multiscale molecular features associated with antibiotic resistance
利用进化分析和机器学习发现与抗生素耐药性相关的多尺度分子特征
- 批准号:
10658686 - 财政年份:2023
- 资助金额:
$ 18.79万 - 项目类别:
Annotating dark ion-channel functions using evolutionary features, machine learning and knowledge graph mining
使用进化特征、机器学习和知识图挖掘注释暗离子通道函数
- 批准号:
10457684 - 财政年份:2022
- 资助金额:
$ 18.79万 - 项目类别:
Annotating dark ion-channel functions using evolutionary features, machine learning and knowledge graph mining (Kennady Boyd)
使用进化特征、机器学习和知识图挖掘注释暗离子通道函数 (Kennady Boyd)
- 批准号:
10809950 - 财政年份:2022
- 资助金额:
$ 18.79万 - 项目类别:
Annotating dark ion-channel functions using evolutionary features, machine learning and knowledge graph mining
使用进化特征、机器学习和知识图挖掘注释暗离子通道函数
- 批准号:
10661550 - 财政年份:2022
- 资助金额:
$ 18.79万 - 项目类别:
Distributed Optimization for Machine Learning on Decentralized Data and Features
基于分散数据和特征的机器学习分布式优化
- 批准号:
RGPIN-2019-04998 - 财政年份:2022
- 资助金额:
$ 18.79万 - 项目类别:
Discovery Grants Program - Individual
Annotating dark ion-channel functions using evolutionary features, machine learning and knowledge graph mining (Rayna Carter)
使用进化特征、机器学习和知识图挖掘注释暗离子通道函数 (Rayna Carter)
- 批准号:
10809931 - 财政年份:2022
- 资助金额:
$ 18.79万 - 项目类别:
Applying machine learning techniques to detect and classify faint tidal features with samples from upcoming large-scale surveys.
应用机器学习技术,利用即将进行的大规模调查的样本来检测和分类微弱的潮汐特征。
- 批准号:
2782601 - 财政年份:2022
- 资助金额:
$ 18.79万 - 项目类别:
Studentship
Distributed Optimization for Machine Learning on Decentralized Data and Features
基于分散数据和特征的机器学习分布式优化
- 批准号:
RGPIN-2019-04998 - 财政年份:2021
- 资助金额:
$ 18.79万 - 项目类别:
Discovery Grants Program - Individual
Comparison of Feature Selection Methods and Machine Learning Classifiers with Computed Tomography Radiomics-based Features for Predicting Chronic Obstructive Pulmonary Disease
特征选择方法和机器学习分类器与基于计算机断层扫描放射组学特征的预测慢性阻塞性肺疾病的比较
- 批准号:
466971 - 财政年份:2021
- 资助金额:
$ 18.79万 - 项目类别:
Studentship Programs