Information storage and retrieval by chaotic neural networks

• Grant number: 02/10707-0
• Support Opportunities: Scholarships abroad - Research
• Start date: March 26, 2003
• End date: August 25, 2003
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Zhao Liang
• Grantee: Zhao Liang
• Host Investigator: Ying Cheng Lai
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Institution abroad: Arizona State University, Phoenix (ASU), United States

Abstract

This research adds to works done over the last decades, which has endeavored to provide biologically plausible, high- performance models of information processing, which have the speed and flexibility of the human (animal) system. Central to this research is the modeling of chaotic neural networks for pattern recognition and pattern analysis, such as invariant pattern feature extraction, image segmentation and recognition, gene expression classification and DNA promotor recognition. The author trusts that the study of nonlinear dynamics and chaos embodied in a network of chaotic elements can help to solve some remained problems of current associative memories, such as capacity of information storage and invariant pattern recognition. (AU)

Scientific publications

(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)

ZHAO‚ L.; PARK‚ K.; LAI‚ Y.C.; CUPERTINO‚ T.H.. Attack induced cascading breakdown in complex networks. Journal of the Brazilian Computer Society, v. 13, n. 3, p. 67-76, 2007. (02/10707-0)

ZHAO‚ L.; CÁCERES‚ J.C.G.; DAMIANCE JR‚ A.P.G.; SZU‚ H.. Chaotic dynamics for multi-value content addressable memory. Neurocomputing, v. 69, n. 13, p. 1628-1636, 2006. (02/10707-0)