## Abstract

This article analyzes dynamics of the chaotic neural network and minimum searching principle of this network. First it is indicated that the dynamics of the chaotic neural network is described like a gradient descent, and the chaotic neural network can roughly find out a local minimum point of a quadratic function using its attractor. Secondly It is guaranteed that the vertex corresponding a local minimum point derived from the chaotic neural network has a lower value of the objective function. Then it is confirmed that the chaotic neural network can escape an invalid local minimum and find out a reasonable one.

Original language | English |
---|---|

Pages (from-to) | 363-369 |

Number of pages | 7 |

Journal | IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences |

Volume | E79-A |

Issue number | 3 |

Publication status | Published - 1996 Jan 1 |

Externally published | Yes |

## Keywords

- Attractor
- Chaos
- Minimum searching problem
- Neural network

## ASJC Scopus subject areas

- Signal Processing
- Computer Graphics and Computer-Aided Design
- Electrical and Electronic Engineering
- Applied Mathematics