期刊文献+

改进的非负稀疏编码神经网络模型及其应用 被引量:2

Modified non-negative sparse coding neural network model and its applications
在线阅读 下载PDF
导出
摘要 提出了一种改进的基于NIG(Normal Inverse Gaussian)密度和稳健主成分分析(PCA)的非负稀疏编码(NNSC)神经网络模型,该模型实质上实现了一个二阶段的学习过程。并利用这个模型成功地建模了视觉感知系统V1区的感受野。该NNSC模型具有很强的自适应于自然数据统计特性的能力。另外,利用类似小波收缩法去噪原理,该模型能够有效地去除图像中的高斯加性噪声,对自然图像编码的仿真实验也表明了该模型在生物学上的合理性和可行性。 This paper proposes a modified Non-Negative Sparse Coding(NNSC) neural network model based on the Normal Inverse Gaussian(NIG) density and robust Principal Component Analysis(PCA).This model implements in fact a two-phase learning.Using this model,the V1 receptive fields of vision-perceptional system can be modeled successfully.Compared with Hoyer's NNSC model,the NIG-based NNSC network behaves stronger capacity of adapting to the statistical properties of natural data.Otherwise,exploiting the similar wavelet shrinkage principle,this model can denoise efficiently the additive Gaussian noise in an image.The simulations of coding on natural images demonstrate this model's plausibility in neuroscience view and feasibility in practical computation.
作者 尚丽
出处 《计算机工程与应用》 CSCD 北大核心 2011年第4期160-164,共5页 Computer Engineering and Applications
基金 国家自然科学基金(No.60970058) 江苏省基础研究计划(自然科学基金)(No.BK2009131) 江苏省"青蓝工程"资助项目 苏州市职业大学青年教师科研启动基金项目(No.SZDQ09L05) 2010苏州市职业大学创新团队资助项目(No.3100125)~~
关键词 正态逆高斯(NIG)密度模型 稳健主成分分析 非负稀疏编码 非负矩阵分解 特征提取 图像去噪 Normal Inverse Gaussian(NIG) density model robust Principal Component Analysis(PCA) non-negative sparse coding non-negative matrix factorization feature extraction image denoising
  • 相关文献

参考文献7

  • 1Hoyer P O.Non-negative sparse coding[C]//Proceedings of the 2001 12th IEEE Workshop on Neural Networks for Signal Processing, Martigny, Switzerland, 2002: 557-565.
  • 2Hoyer P O.Modeling receptive fields with non-negative sparse coding[J].Nerocomputing, 2003,52 (54) : 547-552.
  • 3Olshausen B A, Field D J.Emergence of simple-cell receptive field properties by learning a sparse code for natural images[J]. Nature, 1996,381:607-609.
  • 4Hyvarinen A, Oja E,Hoyer P O,et al.Image feature extraction by sparse coding and independent component analysis[C]//Proc Int Conf on Pattern Recognition (ICPR' 98), Brisbane, Australia, 1998 : 1268-1273.
  • 5Lee D D, Seung H S.Leaming the parts of objects by non-ncgalive matrix factorization[J].Nature, 1999,401 (6755) : 788-791.
  • 6Bandorff-Nielsen O E.Normal inverse Gaussian distributions and stochastic volatility modeling[J].Scand J Statist, 1997,24:1-13.
  • 7Atick J J, Redlich A N.What does the retina know about natural scenes?[J].Neural Computation, 1992,4(4) : 196-210.

同被引文献17

  • 1尚丽,郑春厚.基于稀疏编码的自然图像特征提取及去噪[J].系统仿真学报,2005,17(7):1782-1784. 被引量:12
  • 2Hoyer P O. Modeling Receptive Fields with Non-negative Sparse Coding[J]. Nerocomputing, 2003, 52(54): 547-552.
  • 3Olshausen B A, Field D J. Emergence of Simple-cell Receptive Field Properties by Learning a Sparse Code for Natural Images[J]. Nature, 1996, 381(6583): 607-609.
  • 4Saha B, Adl-Tabatabai A R, Hudson R L, et al. McRT-STM: A High Performance Software Transactional Memory System for a Multi-core Runtime[C] //Proc. of the 11th ACM SIGPLAN Symp. on Principles and Practice of Parallel Programming. [S. 1.] : ACM Press, 2006: 187-197.
  • 5Li Shang.Non-negative sparse coding shrinkage for image denoising using normal inverse Gaussian density model[J].Image and Vision Computing.2008(8)
  • 6Li Shang.Denoising natural images based on a modified sparse coding algorithm[J].Applied Mathematics and Computation.2008(2)
  • 7Patrik O. Hoyer.Modeling receptive fields with non-negative sparse coding[J].Neurocomputing.2003
  • 8Patrik O Hoyer,Aapo Hyv?rinen.A multi-layer sparse coding network learns contour coding from natural images[J].Vision Research.2002(12)
  • 9李乐,章毓晋.SENSC:一个稳定高效的非负稀疏编码算法[J].自动化学报,2009,35(10):1257-1271. 被引量:2
  • 10晁永国,戴芳,韩舒然,何静.改进的非负稀疏编码图像基学习算法[J].计算机工程与科学,2010,32(1):77-79. 被引量:4

引证文献2

二级引证文献2

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