Chaotic neural networks for multi-resolution analysis

Hong Bo Liu, Xiu Kun Wang, Yi Yuan Tang, Shao Zhong Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

In this paper, we investigate new dynamic neural networks for brain data multi-resolution analysis. It is based on chaotic neuron model. Multi-resolution chaotic neural network (MRCNN) architecture is built by cascading the single-layer neural sub-networks, and a higher layer learns to cluster the prototypes developed at the layer directly below it. They have multi-output in coarse-to-fine hierarchical manner, which can reveal the inherent structural characteristic of their input data. A learning processing is also derived from training weights of the networks. They are availably applied to brain data analysis.

Original languageEnglish
Title of host publicationInternational Conference on Machine Learning and Cybernetics
Pages1102-1105
Number of pages4
StatePublished - 2003
EventInternational Conference on Machine Learning and Cybernetics - Xi'an, China
Duration: Nov 2 2003Nov 5 2003

Publication series

NameInternational Conference on Machine Learning and Cybernetics
Volume2

Conference

ConferenceInternational Conference on Machine Learning and Cybernetics
CountryChina
CityXi'an
Period11/2/0311/5/03

Keywords

  • Chaotic Neuron Model
  • Multi-Resolution
  • Neural Network

Fingerprint Dive into the research topics of 'Chaotic neural networks for multi-resolution analysis'. Together they form a unique fingerprint.

  • Cite this

    Liu, H. B., Wang, X. K., Tang, Y. Y., & Zhang, S. Z. (2003). Chaotic neural networks for multi-resolution analysis. In International Conference on Machine Learning and Cybernetics (pp. 1102-1105). (International Conference on Machine Learning and Cybernetics; Vol. 2).