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

最小学习机 被引量：7

On Least Learning Machine
在线阅读 下载PDF
导出
摘要 针对极端学习机(ELM)不能用于多层前向神经网络学习的问题,通过揭示单层前向神经网络(SLFN)的ELM与岭回归以及中心化的岭回归之间的关系,提出了SLFN的最小学习机。通过证明核化的中心化岭回归与核化的PCA之间的关系,提出以无限可微的核函数为激励函数的多层前向神经网络(MLFN)的最小学习机LLM.SLFN/MLFN的最小学习机能够保持ELM的上述优势。 In this paper,the link among extreme learning machine（ELM） for single-layer feedforward neural network（SLFN）and ridge regression and centered ridge regression is theoretically revealed,and accordingly,least learning machine（LLM） is proposed for SLFN.By using iteratively kernelized PCAs ＋ centered ridge regression,LLM for multi-layer feedforward neural network with kernel activation functions is theoretically developed with keeping the same advantage of ELM and LLM for SLFN.
作者 王士同 钟富礼
机构地区 江南大学数字媒体学院 香港理工大学计算机系
出处 《江南大学学报（自然科学版）》 CAS 2010年第5期505-510,共6页 Joural of Jiangnan University (Natural Science Edition)　
基金 国家自然科学基金项目(60903100 60975027 60773206 60704047) 香港理工大学基金项目(Z-08R G-U296) 江苏省自然科学基金项目(BK2009067)
关键词 前向神经网络 核化的PCA算法 极端学习机 最小学习机 feedforward neural network kernelized PCA extreme learning machine least learning machine
分类号 TG580.23 [金属学及工艺—金属切削加工及机床]
  • 相关文献

参考文献19

  • 1HUANG G B, ZHU Q Y, Siew C K. Extreme learning machine: theory and applications [ J]. Neurocomputing, 2006,70: 489-501.
  • 2HUANG G B, DING X, ZHOU H. Optimization method based extreme learning machine for classification [ J/OL l- Neurocomputing, 2010 [ 2010-02-19 ]. http ://www3. ntu. edu. sg/home/egbhuang/NEUCOM-D-lO-00019-Final, pdf.
  • 3HUANG G B, CHEN L, Siew C K. Universal approximation using Incremental constructive feedforward networks with random hidden hodes [ J ]. IEEE Transactions on Neural Networks, 2006,17 (4) :879-892.
  • 4LIANG N Y, HUANG G B, Saratchandran P, et al. A fast and accurate on-line sequential learning algorithm for feedforward networks [ J ]. IEEE Transactions on Neural Networks, 2006,17 ( 6 ) : 1411-1423.
  • 5HUANG G B, ZHU Q Y, Siew C K. Extreme learning machine: a new learning scheme of feedforward neural networks[C]// 2004 International Joint Conference on Neural Networks, (IJCNN2004). Budapest, Hungary: IEEE, 2004.
  • 6RONG H J, HUANG G B, Saratchandran P, et al. On-line sequential fuzzy extreme learning machine for function approximation and classification problems [ J ]. IEEE Transactions on Systems, Man, and Cybernetics : Part B, 2009,39 (4) : 1067-1072.
  • 7FENG G, HUANG G B, LIN Q, et al. Error minimized extreme learning machine with growth of hidden nodes and incremental learning [ J ]. IEEE Transactions on Neural Networks, 2009,20 ( 8 ) : 1352-1357.
  • 8LAN Y, Soh Y C, HUANG G B. Ensemble of online sequential extreme learning machine [ J]. Neurocomputing, 2009,72: 3391-3395.
  • 9LI M B, HUANG G B, Saratchandran P, et al. Fully complex extreme learning machine [ J]. Neurocomputing, 2005,68: 306-314.
  • 10HUANG G B, CHEN L. Convex incremental extreme learning machine[ J]. Neurocomputing, 2007,70:3056-3062.

二级参考文献18

  • 1杨健,杨静宇,叶晖.Fisher线性鉴别分析的理论研究及其应用[J].自动化学报,2003,29(4):481-493. 被引量：96
  • 2VAPNIK V.Statistical learning theory[M].New York:Wiley,1998:13-18.
  • 3SCHOLKOPF B,SMOLA A.Learning with kernels[M].Cambridge,USA:MIT Press,2002:25-32.
  • 4ER M J,CHEN W,WU S.High-speed face recognition based on discrete cosine transform and RBF neural networks[J].IEEE Transanctions on Neural Networks,2005,16(3):679-691.
  • 5TONG S,CHANG E.Support vector machine active learning for image retrieval[C] //Proceedings of ACM International Conference on Multimedia.2001:107-118.
  • 6GANAPATHIRAJU A,HAMAKER J E,PICONE J.Applications of support vector machines to speech recognition[J].IEEE Transactions on Signal Processing,2004,52(8):2348-2355.
  • 7KIRA K,RENDELL L A.A practical approach to feature selection[C] //Proc Ninth Int'l Conf on Machine Learning.[S.l.] ,1992:249-256.
  • 8SUN Y J.Iterative RELIEF for feature weighting:algorithms,theories,and applications[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2007,29(6):1035-1051.
  • 9QIU X,WU L.Face Recognition by stepwise nonparametric margin maximum criterion[C] //Proc ICCV.2005:1567-1572.
  • 10WANG F,ZHANG C S.Feature extraction by maximizing the average neighborhood margin[C] //Proc ICCV.Beijing,2007:1-8.

共引文献2

同被引文献31

  • 1陈德旺,蔡际杰,黄允浒.面向可解释性人工智能与大数据的模糊系统发展展望[J].智能科学与技术学报,2019,1(4):327-334. 被引量：19
  • 2王素芬.模糊系统与神经网络结合的现状[J].网络与信息,2007,21(5):69-69. 被引量：1
  • 3Hornik K. Approximation capabilities of feedforward networks[J].{H}NEURAL NETWORKS,1991,(02):251-257.
  • 4Leshno M,Lin V Y,Pinkus A. Multilayer feedforward networks with a nonpolynomial activation function can approximate any function[J].{H}NEURAL NETWORKS,1993,(06):861-867.
  • 5HUANG G B,ZHU Q Y,Siew C K. Extreme learning machine:theory and applications[J].{H}NEUROCOMPUTING,2006.489-501.
  • 6DU K L,Swamy M N S. Neural Networks in a Softcomputing Framework[M].{H}London:Springer-Verlag,2006.
  • 7WANG S T,WANG J,CHUNG F L. Kernel density estimation,kernel methods,and fast learning in large data sets[J].IEEE Transactions on Cybernetics,2013,(99):1-20.
  • 8Friedman J H. Multivariate adaptive regression splines (with discussion)[J].{H}ANNALS OF STATISTICS,1991,(01):1-141.
  • 9ZHANG C,NIE F,XIANG S. A general kernelization framework for learning algorithms based on kernel PCA[J].{H}NEUROCOMPUTING,2010,(4/5/6):959-967.
  • 10YANG J,ZHANG D,Frangi A F. Two-dimensional PCA:a new approach to appearance-based face representation and recognition[J].{H}IEEE Transactions on Pattern Analysis and Machine Intelligence,2004,(01):131-137.

引证文献7

二级引证文献50

江南大学学报（自然科学版）
2010年 第5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