### Abstract

We apply evolutionary computations to Hopfield's neural network model of associative memory. In the Hopfield model, almost infinite number of combinations of synaptic weights give a network a function of associative memory. Furthermore, there is a trade-off between the storage capacity and size of basin of attraction. Therefore, the model can be thought of as a test suite of multi-modal and/or multi-objective function optimization. As preliminary stages, we investigate the basic behaviors of associative memory under simple evolutionary processes. In this paper, we present some experiments using an evolution strategy.

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

Title of host publication | Proceedings of the IEEE Conference on Evolutionary Computation, ICEC |

Editors | Anon |

Publisher | IEEE |

Pages | 679-683 |

Number of pages | 5 |

Publication status | Published - 1997 |

Externally published | Yes |

Event | Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97 - Indianapolis, IN, USA Duration: Apr 13 1997 → Apr 16 1997 |

### Other

Other | Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97 |
---|---|

City | Indianapolis, IN, USA |

Period | 4/13/97 → 4/16/97 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Computer Science(all)
- Engineering(all)

### Cite this

*Proceedings of the IEEE Conference on Evolutionary Computation, ICEC*(pp. 679-683). IEEE.

**Application of an evolution strategy to the Hopfield model of associative memory.** / Imada, Akira; Araki, Keijiro.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*Proceedings of the IEEE Conference on Evolutionary Computation, ICEC.*IEEE, pp. 679-683, Proceedings of the 1997 IEEE International Conference on Evolutionary Computation, ICEC'97, Indianapolis, IN, USA, 4/13/97.

}

TY - GEN

T1 - Application of an evolution strategy to the Hopfield model of associative memory

AU - Imada, Akira

AU - Araki, Keijiro

PY - 1997

Y1 - 1997

N2 - We apply evolutionary computations to Hopfield's neural network model of associative memory. In the Hopfield model, almost infinite number of combinations of synaptic weights give a network a function of associative memory. Furthermore, there is a trade-off between the storage capacity and size of basin of attraction. Therefore, the model can be thought of as a test suite of multi-modal and/or multi-objective function optimization. As preliminary stages, we investigate the basic behaviors of associative memory under simple evolutionary processes. In this paper, we present some experiments using an evolution strategy.

AB - We apply evolutionary computations to Hopfield's neural network model of associative memory. In the Hopfield model, almost infinite number of combinations of synaptic weights give a network a function of associative memory. Furthermore, there is a trade-off between the storage capacity and size of basin of attraction. Therefore, the model can be thought of as a test suite of multi-modal and/or multi-objective function optimization. As preliminary stages, we investigate the basic behaviors of associative memory under simple evolutionary processes. In this paper, we present some experiments using an evolution strategy.

UR - http://www.scopus.com/inward/record.url?scp=0030682001&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030682001&partnerID=8YFLogxK

M3 - Conference contribution

SP - 679

EP - 683

BT - Proceedings of the IEEE Conference on Evolutionary Computation, ICEC

A2 - Anon, null

PB - IEEE

ER -