Fast, Locally Adaptive Inference for Machine Learning in Graphical Models
图形模型中机器学习的快速、局部自适应推理
基本信息
- 批准号:EP/J00104X/1
- 负责人:
- 金额:$ 11.94万
- 依托单位:
- 依托单位国家:英国
- 项目类别:Research Grant
- 财政年份:2011
- 资助国家:英国
- 起止时间:2011 至 无数据
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Graphical models are a powerful tool in machine learning with successful applications in diverse areas such as medical diagnosis, natural language processing, robotics, speech recognition and analysis of genetic data. Despite this success, modern data sets place new demands on the graphical modelling framework, because the models can be enormous, but exact inference in graphical models is intractable. Despite the extensive literature on approximate inference, there is still a huge gap between the largest data sets that we wish to analyse and the largest graphical models that we can handle.In order to meet the challenges of these new applications, this project concerns new approximate inference algorithms for the large-scale graphical models that arise in practical applications of machine learning. Very few existing inference algorithms can handle extremely large models with continuous variables, and important classes of inference algorithms, such as Monte Carlo techniques, have not been scaled to such models at all. Computationally efficient inference would significantly expand the range of applications to which the graphical modelling framework can be applied.
图形模型是机器学习中一个强大的工具,在医学诊断、自然语言处理、机器人、语音识别和基因数据分析等各个领域都有成功的应用。尽管取得了这样的成功,但现代数据集对图形建模框架提出了新的要求,因为模型可能是巨大的,但图形模型中的精确推断是难以处理的。尽管有大量关于近似推理的文献,但在我们希望分析的最大数据集和我们可以处理的最大图形模型之间仍然存在巨大差距。为了应对这些新应用的挑战,本项目关注机器学习实际应用中出现的大规模图形模型的新近似推理算法。很少有现有的推理算法可以处理具有连续变量的超大模型,而重要的推理算法类别,如蒙特卡罗技术,根本没有扩展到这样的模型。计算效率高的推理将显著扩展图形建模框架的应用范围。
项目成果
期刊论文数量(5)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Word Storms: Multiples of Word Clouds for Visual Comparison of Documents
文字风暴:用于文档视觉比较的多个文字云
- DOI:10.48550/arxiv.1301.0503
- 发表时间:2013
- 期刊:
- 影响因子:0
- 作者:Castella Quim
- 通讯作者:Castella Quim
Semi-Separable Hamiltonian Monte Carlo for Inference in Bayesian Hierarchical Models
用于贝叶斯分层模型推理的半可分离哈密顿蒙特卡罗
- DOI:10.48550/arxiv.1406.3843
- 发表时间:2014
- 期刊:
- 影响因子:0
- 作者:Zhang Yichuan
- 通讯作者:Zhang Yichuan
Continuous Relaxations for Discrete Hamiltonian Monte Carlo
- DOI:
- 发表时间:2012-12
- 期刊:
- 影响因子:6.2
- 作者:Yichuan Zhang;Charles Sutton;A. Storkey;Zoubin Ghahramani
- 通讯作者:Yichuan Zhang;Charles Sutton;A. Storkey;Zoubin Ghahramani
{{
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 }}
Charles Sutton其他文献
Neural Variational Inference For Topic Models
主题模型的神经变分推理
- DOI:
- 发表时间:
2016 - 期刊:
- 影响因子:0
- 作者:
Akash Srivastava;Charles Sutton - 通讯作者:
Charles Sutton
Conditional Independence by Typing
通过键入实现条件独立
- DOI:
- 发表时间:
2020 - 期刊:
- 影响因子:1.3
- 作者:
Maria I. Gorinova;A. Gordon;Charles Sutton;Matthijs Vákár - 通讯作者:
Matthijs Vákár
Compact Explanations of Why Malware is Bad
恶意软件为何不好的简要解释
- DOI:
- 发表时间:
2015 - 期刊:
- 影响因子:0
- 作者:
Wei Chen;Charles Sutton;A. Gordon;David Aspinall;Igor Muttik;Qi Shen - 通讯作者:
Qi Shen
Verifying Anti-Security Policies Learnt from Android Malware Families
验证从 Android 恶意软件家族学到的反安全策略
- DOI:
- 发表时间:
2015 - 期刊:
- 影响因子:0
- 作者:
Wei Chen;Charles Sutton;David Aspinall;A. Gordon;Qi Shen;Igor Muttik - 通讯作者:
Igor Muttik
Incremental Sampling Without Replacement for Sequence Models
无需替换序列模型的增量采样
- DOI:
- 发表时间:
2020 - 期刊:
- 影响因子:0
- 作者:
Kensen Shi;David Bieber;Charles Sutton - 通讯作者:
Charles Sutton
Charles Sutton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('Charles Sutton', 18)}}的其他基金
LUCID: Clearer Software by Integrating Natural Language Analysis into Software Engineering
LUCID:通过将自然语言分析集成到软件工程中来更清晰的软件
- 批准号:
EP/P005314/1 - 财政年份:2017
- 资助金额:
$ 11.94万 - 项目类别:
Research Grant
Statistical Natural Language Processing Methods for Computer Program Source Code
计算机程序源代码的统计自然语言处理方法
- 批准号:
EP/K024043/1 - 财政年份:2013
- 资助金额:
$ 11.94万 - 项目类别:
Research Grant
相似海外基金
Towards innovative and affordable sodium- and zinc-based energy storage systems based on more sustainable and locally-sourced materials (eNargiZinc)
开发基于更可持续和本地采购的材料的创新且经济实惠的钠基和锌基储能系统 (eNargiZinc)
- 批准号:
EP/Y03127X/1 - 财政年份:2024
- 资助金额:
$ 11.94万 - 项目类别:
Research Grant
CAREER: Topology, Spectral Geometry, and Arithmetic of Locally Symmetric Spaces
职业:拓扑、谱几何和局部对称空间算术
- 批准号:
2338933 - 财政年份:2024
- 资助金额:
$ 11.94万 - 项目类别:
Continuing Grant
PFI-TT: Water disinfection using safe and sustainable copper combined with a locally enhanced electric field
PFI-TT:使用安全且可持续的铜结合局部增强电场进行水消毒
- 批准号:
2329669 - 财政年份:2024
- 资助金额:
$ 11.94万 - 项目类别:
Continuing Grant
Towards innovative and affordable sodium- and zinc-based energy storage systems based on more sustainable and locally-sourced materials
开发基于更可持续和本地采购的材料的创新且经济实惠的钠基和锌基储能系统
- 批准号:
EP/Y031253/1 - 财政年份:2024
- 资助金额:
$ 11.94万 - 项目类别:
Research Grant
C*-simplicity of locally compact groups
C*-局部紧群的简性
- 批准号:
23KJ0560 - 财政年份:2023
- 资助金额:
$ 11.94万 - 项目类别:
Grant-in-Aid for JSPS Fellows
Immunogenomic predictors of outcomes in patients with locally advanced cervical cancer treated with immunotherapy and chemoradiation
接受免疫治疗和放化疗的局部晚期宫颈癌患者结果的免疫基因组预测因子
- 批准号:
10908093 - 财政年份:2023
- 资助金额:
$ 11.94万 - 项目类别:
Magnetic imaging by the locally induced anomalous Nernst effect using atomic force microscopy
使用原子力显微镜通过局部诱发的异常能斯特效应进行磁成像
- 批准号:
23K04579 - 财政年份:2023
- 资助金额:
$ 11.94万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
DMREF/Collaborative Research: Active Learning-Based Material Discovery for 3D Printed Solids with Locally-Tunable Electrical and Mechanical Properties
DMREF/协作研究:基于主动学习的材料发现,用于具有局部可调电气和机械性能的 3D 打印固体
- 批准号:
2323696 - 财政年份:2023
- 资助金额:
$ 11.94万 - 项目类别:
Standard Grant
Locally Driven Approaches to Valued Pedagogies: A Comparative Study between Eastern and Western Africa and Latin America
本地驱动的有价值的教学法:东西非和拉丁美洲之间的比较研究
- 批准号:
22KK0207 - 财政年份:2023
- 资助金额:
$ 11.94万 - 项目类别:
Fund for the Promotion of Joint International Research (Fostering Joint International Research (A))
A Phase I Proof-of-Concept Study of CBL0137 Combined with Ipilimumab and Nivolumab Therapy in Locally Advanced or Metastatic Melanoma
CBL0137 联合 Ipilimumab 和 Nivolumab 治疗局部晚期或转移性黑色素瘤的 I 期概念验证研究
- 批准号:
10722873 - 财政年份:2023
- 资助金额:
$ 11.94万 - 项目类别: