A novel Hebbian rules based method for computation of sparse coding basis vectors

  • Authors:

  • Baixian Zou;Jun Miao;Xiaoling Yang;Lijuan Duan;Yuanhua Qiao

  • Affiliations:

  • Department of Information Science and Technology, College of Arts and Science, Beijing Union University, Beijing, China;Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Tianjin Academy of Agricultural Science, Tianjin, China;College of Computer Science and Technology, Beijing University of Technology, Beijing, China;College of Applied Science, Beijing University of Technology, Beijing, China

  • Venue:
  • ICNC'09 Proceedings of the 5th international conference on Natural computation
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

Sparse coding has high-performance encoding and ability to express images, sparse encoding basis vector plays a crucial role. The computational complexity of the most existing sparse coding basis vectors of is relatively large. In order to reduce the computational complexity and save the time to train basis vectors. A new Hebbian rules based method for computation of sparse coding basis vectors is proposed in this paper. A two-layer neural network is constructed to implement the task. The main idea of our work is to learn basis vectors by removing the redundancy of all initial vectors using Hebbian rules. The experiments on natural images prove that the proposed method is effective for sparse coding basis learning. It has the smaller computational complexity compared with the previous work.