期刊文献+

基于PSO算法与Dropout的改进CNN算法 被引量:6

An improved CNN algorithm based on PSO and dropout
下载PDF
导出
摘要 设计卷积升级网络结构,引入PSO算法减小了误差的反向传播,避免了滞后误差与图像的过拟合,提高了收敛速度。将该方法应用到数据集HCL2000和MNIST上,并进行了与WCNN、MLP-CNN、SVM-ELM的实验对比,证明了改进算法的正确性。 A convolution upgrade network structure is designed, and then PSO algorithm is introduced to reduce the error back propagation. Accordingly, the over-fit between delayed error and image is avoided for improving convergent speed. The method is applied to data set HCL2000 and MNIST, and experiments compared with WCNN, MLP-CNN and SVM-ELM are carried.
作者 王金哲 王泽儒 王红梅 WAN Jinzhe;WANG Zeru;WANG Hongmei(School of Computer Science&Engineering,Changchun University of Technology,Changchun 130012,China)
出处 《长春工业大学学报》 CAS 2019年第1期26-30,共5页 Journal of Changchun University of Technology
基金 吉林省科技厅科技发展计划基金资助项目(20160203010GX)
关键词 粒子群算法 CNN DROPOUT 过拟合 Particle swarm optimization CNN Dropout over-fit
  • 相关文献

参考文献4

二级参考文献75

  • 1Femdndez-Delgado M, Cemadas E,Barro S, et al. Dowe Need Hundreds of Classifiers to Solve Real WorldClassification Problems? [J]. Journal of MachineLearning Research (SI 532-4435), 2014, 15(1):3133-3181.
  • 2Joachims T. Making Large-scale Support VectorMachine Learning Practical [C]// Advances in kernelmethods. USA: MIT Press, 1999: 169-184.
  • 3Harada T, Ushiku Y,Yamashita Y,et al. DiscriminativeSpatial Pyramid [C]// Computer Vision and PatternRecognition (CVPR), 2011 IEEE Conference on. USA:IEEE, 2011: 1617-1624.
  • 4S 6 nchez J, Perronnin F, Mensink T, et al. ImageClassification with the Fisher Vector; Theory andPractice [J]. International Journal of Computer Vision(S0920-5691), 2013, 105(3): 222-245.
  • 5Zhang C, Liu J, Tian Q, et al. Image Classification byNon-negative Sparse Coding, Low-rank and SparseDecomposition [C]// Computer Vision and PatternRecognition (CVPR), 2011 IEEE Conference on. USA:IEEE, 2011: 1673-1680.
  • 6Boureau Y L, Bach F, LeCun Y,et al. Learningmid-level features for recognition[C]//Computer Visionand Pattern Recognition (CVPR), 2010 IEEEConference on. USA:IEEE,2010: 2559-2566.
  • 7Lecun Y, Kavukcuoglu K, Farabet C. ConvolutionalNetworks and Applications in Vision [C]// Circuits andSystems (ISCAS), Proceedings of 2010 IEEEInternational Symposium on. USA: IEEE, 2010: 253-256.
  • 8Bouvrie J. Notes on Convolutional Neural Networks[R]// MIT-CBCL Technical Reports. Germany: SpringerInternational, 2006: 38-44.
  • 9Fischer A, Igel C. Training Restricted BoltzmannMachines: An Introduction [J]. Pattern Recognition(S0031-3203), 2014, 47(1): 25-39.
  • 10Tang Y, Salakhutdinov R, Hinton G. Robust BoltzmannMachines for Recognition and Denoising [C]// ComputerVision and Pattern Recognition (CVPR), 2012 IEEEConference on. USA: IEEE, 2012: 2264-2271.

共引文献1840

同被引文献24

引证文献6

二级引证文献13

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