期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

遗传顺序IB算法 被引量：1

Genetic Sequential IB Algorithm
在线阅读 下载PDF
导出
摘要 本文提出一种遗传顺序IB算法,该算法以基本顺序IB算法的多次运行结果作为初始种群,并基于集成操作算子将初始种群组合为一个解;然后算法分别计算解中每个元素的不确定性统计量,对解中元素进行选择和变异,最后经过若干代变异后得到优化的解.在数据集上的实验结果表明,相对于顺序IB算法,遗传顺序IB算法具有运行效率高、解更优化的特点. This paper proposes a genetic sequential IB algorithm. R takes several seeding solutions of the basic sequential IB algorithm as initial population, and then integrates this population into a solution using the integration operator. Sequentially, some certain positions of the obtained solution are selected and mutated iteratively based on the defined instability statistic. After mutation of several generations, the iterative process terminates and a more optimal solution is obtained. Experimental results on the benchmark data sets indicate that the proposed algorithm outperforms the sequential IB algorithm in both the accuracy and the efficiency.
作者 袁华强 叶阳东 刘东
机构地区 东莞理工学院工程技术学院 郑州大学信息工程学院
出处 《电子学报》 EI CAS CSCD 北大核心 2009年第8期1804-1809,共6页 Acta Electronica Sinica
基金 国家自然科学基金(No.60573029 No.60773048 No.60773050)
关键词 IB理论 SIB算法 遗传变异 互信息 IB theory sIB algorithm genetic variation mutual information
分类号 TP391 [自动化与计算机技术—计算机应用技术]
  • 相关文献

参考文献11

  • 1N Tishby, F Pereira, W Bialek. The information bottieneck method[ A] .Proc of 37th Allerton Conference on Communication, Control and Computing [ C ]. Monticello, Blinois: Curran Associates, Inc., 1999.368 - 377.
  • 2N Slonim, N Friedman, N Tishby. Unsupervised document classification using sequential information maximization[ A ]. Proc of the 25th Ann Int ACM SIGIR Conf on Research and Development in Information Retrieval[ C]. Tampere Finland: ACM, 2002.129 - 136.
  • 3N Slonim, N Tishby. The Power of Word Clusters for Text Classificationl Al. Proc of 23rd European Colloquium on Informarion Retrieval Research [C]. Darmstadt: Springer Verlag, 2001.1 - 12.
  • 4S Gordon, H Greenspan, J Goldberger. Applying the Information Bottleneck Principle to Unsupervised Clustering of and Continuous Image Representations[ A]. Proc of the 9th International Conference on Computer Vision[ C]. Nice, France: IEEE Computer Society, 2003. 370- 377.
  • 5N Slonim, R Somerville, N Tishby, et al. Objective classification of galaxies spectra using the information bottleneck method [ J] .Monthly Notices of the Royal Astronomical Society,2001 (323) :270 - 284.
  • 6N Tishby, N Slonim. Data clustering by Markovian relaxation and the information bottleneck method[ A ]. Proc of Advances in Neural Information Processing Systems[ C]. Vancouver: MIT Press, 2001.640 - 646.
  • 7E Schneidman, W Bialek, M J Berry. An information theoretic approach to the functional classification of neurons [A ]. Proc Advances in Neural Information Processing Systems[ C]. Vancouver: MIT Press,2002. 197 - 204.
  • 8M Gorodetsky. Methods for discovering semantic relations between words based on co-occurrence patterns in corpora[ D ]. Jerusalem: Hebrew university, Israel,2002.
  • 9N Slonim. The information bottleneck: Theory and Application [D]. Jerusalem: Hebrew University, Israel, 2002.
  • 10N Slonim, N Tishby. Agglomerative information bottleneck [A]. Proc of Advances in Neural Information Processing Systems[ C]. Denver: MIT Press, 1999.617 - 623.

同被引文献20

  • 1朱真峰,叶阳东,Gang Li.基于变异的迭代sIB算法[J].计算机研究与发展,2007,44(11):1832-1838. 被引量：5
  • 2Tishby N, Pereira F, Bialek W. The information bottleneck method[A] .Proceedings of 37th Allerton Conference on Com- munication, Control and Computing[C]. Monticello, IL:IEEEE Press, 1999.368 - 377.
  • 3Slonim N, Tishby N. Agglomerative information bottleneck [A]. Proceedings of Advances in Neural Information Process- ing Systems[C]. Denver, CO: MIT Press, 1999.617 - 623.
  • 4Slonim N, Friedman N, Tishby N. Unsupervised document clas- sification using sequential information maximization[A]. Pro- ceedings of 25th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval [C]. Tampere, Finland: ACM Press,2002. 129 - 136.
  • 5Slonim N. The information bottleneck: theory and application [D]. Jerusalem: The Hebrew University of Jerusalem, 2002.
  • 6Goldlxwger J, Gordon S, Greenspan H. Unsupervised image-set clustering using an information theoretic framework [J]. IF.EF. Transactions on Image Processing, 2006,15 (2) : 449 - 458.
  • 7Bardera A, Rigan J,Baoda I,et al. Image segmentation using information bottleneck method[J]. IEEE Transactions on Image Processing,2009,18(7) : 1601 - 1612.
  • 8Lou Z, Ye Y, Yan X. The multi-feature information bottleneck with application to unsupervised image categorization[A]. Pro- ceedings of 23rd International Joint Conference on Artificial In- telligence[C]. Beijing, China: AAAI Press, 2013.1508 - 1515.
  • 9Hecht R, Noor E, Tishby N. Speaker recognition via gaussian information bottleneck [A]. Proceedings of InterSpeech [C]. Brighton, UK: ISCA Press,2009.1567 - 1570.
  • 10Lazebnik S, Raginsky M. Supervised learning of quantizer codebooks by information loss minimization[J]. IEEE Trans- actions on Pattern Analysis and Machine Intelligence, 2009, 31(7) : 1294 - 1309.

引证文献1

二级引证文献2

电子学报
2009年 第8期

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部