The second order mean field approximation of graphical models and its application to Bayesian inference

图模型的二阶平均场逼近及其在贝叶斯推理中的应用

基本信息

  • 批准号:
    17500088
  • 负责人:
  • 金额:
    $ 2.41万
  • 依托单位:
  • 依托单位国家:
    日本
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
  • 财政年份:
    2005
  • 资助国家:
    日本
  • 起止时间:
    2005 至 2007
  • 项目状态:
    已结题

项目摘要

Markov random field (MRF) and its discriminative version have been shown useful for both biological analysis and practical applications. In biological analysis, the debate on neuronal correlations is now continuing in which the analysis of the probability P( r| s) of the neuronal response r conditional on a stimulus s is required, which could be modeled with MRF. In this context the importance of a parametric model for analyzing correlations by modeling joint probability P(r, s) is shown using Gibbs distribution.Several approximation techniques have been proposed for computing state probabilities of MRFs, CRFs, including belief propagation, which is not applicable for MRFs in a general situation. Mean field approximation (MRF) is known as only the generally applicable approximation technique at present.To improve the accuracy of the mean-field approximation several advanced techniques have been proposed. Since the better accuracy we attain, the more intricate equations we get into, it … More becomes hard to know the efficient training procedure. In fact the training procedure is known only for the naive mean-field approximation (NMF), which is not so sufficient for the approximation accuracy.The achievement of this research is to have refined the mean field approximation to alleviate both the testing and learning time, and to have shown the efficient learning scheme for object recognition with the variational phasor mean field model (VPMF). The striking result is that our learning scheme shows comparable testing performance with SVM, despite using much smaller size of training data, and in addition the detection time and the training time are much smaller than SVM based face detection.Performance evaluation of VPMF is given for approximation accuracy, the local minima, and a face recognition problems. We have also attained the conclusion that the correlation of population coding in neural networks is more powerful than just using only the mean firing rate.Performance evaluation of VPMF is given for approximation accuracy, the local minima, and a face recognition problems. Less
马尔可夫随机场(MRF)及其判别式已被证明是有用的生物分析和实际应用。在生物学分析中,关于神经元相关性的争论现在仍在继续,其中概率P(r|需要以刺激s为条件的神经元反应r的s),这可以用MRF建模。在这种情况下,一个参数模型的重要性,分析相关性建模联合概率P(r,s)使用Gibbs distribution.Several近似技术已经提出了计算状态概率的MRF,CRF,包括信念传播,这是不适用于MRF在一般情况下。平均场近似(MRF)是目前已知的唯一普遍适用的近似方法,为了提高平均场近似的精度,人们提出了几种改进的方法。由于我们获得的精度越高,我们进入的方程就越复杂, ...更多信息 很难知道有效的训练程序。实际上,训练过程仅针对朴素平均场近似(NMF)而已知,这对于近似精度不是那么充分。本研究的成果是改进平均场近似以减轻测试和学习时间,并且显示了用于对象识别的有效学习方案与变分相量平均场模型(VPMF)。引人注目的结果是,我们的学习方案显示出与SVM相媲美的测试性能,尽管使用更小的训练数据的大小,此外,检测时间和训练时间是远远小于基于SVM的人脸detection.Performance评估VPMF的近似精度,局部极小值,和人脸识别问题。我们还得到了这样的结论,即在神经网络中群体编码的相关性比仅仅使用平均发射率更强大. VPMF的性能评估给出的近似精度,局部极小值,和人脸识别问题.少

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)
カーネル主成分分析を用いた学習機械のパラメタ自動決定法
基于核主成分分析的学习机参数自动确定方法
  • DOI:
  • 发表时间:
    2007
  • 期刊:
  • 影响因子:
    0
  • 作者:
    関口涼平;高橋治久;堀田一弘
  • 通讯作者:
    堀田一弘
Variational phasor mean field model for object recognition
カーネル主成分分析を用いた学習機械のパラメータ自動決定法
基于核主成分分析的学习机参数自动确定方法
Phasor Mean Field Model for Image Processing
用于图像处理的相量平均场模型
One-class SVMを用いた顕微鏡画像からの粒子検出と計数
使用一类 SVM 从显微图像中检测和计数颗粒
  • DOI:
  • 发表时间:
    2008
  • 期刊:
  • 影响因子:
    0
  • 作者:
    久場日暖;堀田 一弘;高橋治久
  • 通讯作者:
    高橋治久
{{ 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 }}

TAKAHASHI Haruhisa其他文献

TAKAHASHI Haruhisa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('TAKAHASHI Haruhisa', 18)}}的其他基金

Generative model in a wide class of distribution and its application
广义分布中的生成模型及其应用
  • 批准号:
    24500165
  • 财政年份:
    2012
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Machine learning via fusion of discriminative and mean field models and its application to image recognition
通过融合判别模型和平均场模型的机器学习及其在图像识别中的应用
  • 批准号:
    21500213
  • 财政年份:
    2009
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Information separation via phasor neural networks and its application
相量神经网络信息分离及其应用
  • 批准号:
    13650402
  • 财政年份:
    2001
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Real-time speech recognition and model selection via recurrent neural networks
通过循环神经网络进行实时语音识别和模型选择
  • 批准号:
    06650401
  • 财政年份:
    1994
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Grant-in-Aid for General Scientific Research (C)
Mamalian-like neural networks for dynamic information processing and its learning algorithm
用于动态信息处理的类哺乳动物神经网络及其学习算法
  • 批准号:
    04805032
  • 财政年份:
    1992
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Grant-in-Aid for General Scientific Research (C)
Development and Applications of Learning Algorithms for Neural Networks
神经网络学习算法的开发和应用
  • 批准号:
    02650235
  • 财政年份:
    1990
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Grant-in-Aid for General Scientific Research (C)

相似海外基金

BCSP: ABI Innovation: Collaborative Research: Predicting changes in protein activity from changes in sequence by identifying the underlying Biophysical Conditional Random Field
BCSP:ABI 创新:协作研究:通过识别潜在的生物物理条件随机场,根据序列变化预测蛋白质活性的变化
  • 批准号:
    1262457
  • 财政年份:
    2014
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Standard Grant
BCSP: ABI Innovation: Collaborative Research: Predicting changes in protein activity from changes in sequence by identifying the underlying Biophysical Conditional Random Field
BCSP:ABI 创新:协作研究:通过识别潜在的生物物理条件随机场,根据序列变化预测蛋白质活性的变化
  • 批准号:
    1262469
  • 财政年份:
    2014
  • 资助金额:
    $ 2.41万
  • 项目类别:
    Standard Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了