### Abstract

In contrast to the usual types of neural networks which utilize two states for each neuron, a class of synchronous discrete-time multilevel threshold neural networks is developed. A qualitative analysis and a synthesis procedure of the class of neural networks constitute the principal contributions of this work. The applicability of the class of neural networks is demonstrated by means of a gray-level image processing example in which each neuron of the present model assumes one of 16 values. In doing so, the number of neurons and the number of interconnections are reduced, when compared to the usual binary state networks.

Original language | English (US) |
---|---|

Title of host publication | Proceedings - IEEE International Symposium on Circuits and Systems |

Publisher | Publ by IEEE |

Pages | 1461-1464 |

Number of pages | 4 |

Volume | 3 |

State | Published - 1991 |

Externally published | Yes |

Event | 1991 IEEE International Symposium on Circuits and Systems Part 4 (of 5) - Singapore, Singapore Duration: Jun 11 1991 → Jun 14 1991 |

### Other

Other | 1991 IEEE International Symposium on Circuits and Systems Part 4 (of 5) |
---|---|

City | Singapore, Singapore |

Period | 6/11/91 → 6/14/91 |

### Fingerprint

### ASJC Scopus subject areas

- Electrical and Electronic Engineering
- Electronic, Optical and Magnetic Materials

### Cite this

*Proceedings - IEEE International Symposium on Circuits and Systems*(Vol. 3, pp. 1461-1464). Publ by IEEE.

**Analysis and synthesis of discrete-time neural networks with multilevel threshold functions.** / Si, Jennie; Michel, A. N.

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

*Proceedings - IEEE International Symposium on Circuits and Systems.*vol. 3, Publ by IEEE, pp. 1461-1464, 1991 IEEE International Symposium on Circuits and Systems Part 4 (of 5), Singapore, Singapore, 6/11/91.

}

TY - GEN

T1 - Analysis and synthesis of discrete-time neural networks with multilevel threshold functions

AU - Si, Jennie

AU - Michel, A. N.

PY - 1991

Y1 - 1991

N2 - In contrast to the usual types of neural networks which utilize two states for each neuron, a class of synchronous discrete-time multilevel threshold neural networks is developed. A qualitative analysis and a synthesis procedure of the class of neural networks constitute the principal contributions of this work. The applicability of the class of neural networks is demonstrated by means of a gray-level image processing example in which each neuron of the present model assumes one of 16 values. In doing so, the number of neurons and the number of interconnections are reduced, when compared to the usual binary state networks.

AB - In contrast to the usual types of neural networks which utilize two states for each neuron, a class of synchronous discrete-time multilevel threshold neural networks is developed. A qualitative analysis and a synthesis procedure of the class of neural networks constitute the principal contributions of this work. The applicability of the class of neural networks is demonstrated by means of a gray-level image processing example in which each neuron of the present model assumes one of 16 values. In doing so, the number of neurons and the number of interconnections are reduced, when compared to the usual binary state networks.

UR - http://www.scopus.com/inward/record.url?scp=0026370238&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026370238&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026370238

VL - 3

SP - 1461

EP - 1464

BT - Proceedings - IEEE International Symposium on Circuits and Systems

PB - Publ by IEEE

ER -