### Abstract

Fuzzy logic, neural network architectures and learning are integrated and unified. Learning fuzzy rules from data, may it be for classification or function approximation, are the same with training radial basis function (RBF) networks from the same data. Fuzzy logic learning algorithms satisfy the learning principles defined by the learning theory for neural networks. The learning principles not only require the algorithm to design and train the net in polynomial time, but attempts to generate the smallest possible net which attempts to generate the smallest set of fuzzy rules to describe the phenomenon. It implies generalization in learning and polynomial time complexity of learning algorithms.

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

Title of host publication | IEEE International Conference on Neural Networks - Conference Proceedings |

Place of Publication | Piscataway, NJ, United States |

Publisher | IEEE |

Pages | 522-527 |

Number of pages | 6 |

Volume | 1 |

State | Published - 1997 |

Event | Proceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4) - Houston, TX, USA Duration: Jun 9 1997 → Jun 12 1997 |

### Other

Other | Proceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4) |
---|---|

City | Houston, TX, USA |

Period | 6/9/97 → 6/12/97 |

### Fingerprint

### ASJC Scopus subject areas

- Software
- Control and Systems Engineering
- Artificial Intelligence

### Cite this

*IEEE International Conference on Neural Networks - Conference Proceedings*(Vol. 1, pp. 522-527). Piscataway, NJ, United States: IEEE.

**Fuzzy logic, neural networks, and brain-like learning.** / Roy, Asim; Miranda, Raymond.

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

*IEEE International Conference on Neural Networks - Conference Proceedings.*vol. 1, IEEE, Piscataway, NJ, United States, pp. 522-527, Proceedings of the 1997 IEEE International Conference on Neural Networks. Part 4 (of 4), Houston, TX, USA, 6/9/97.

}

TY - GEN

T1 - Fuzzy logic, neural networks, and brain-like learning

AU - Roy, Asim

AU - Miranda, Raymond

PY - 1997

Y1 - 1997

N2 - Fuzzy logic, neural network architectures and learning are integrated and unified. Learning fuzzy rules from data, may it be for classification or function approximation, are the same with training radial basis function (RBF) networks from the same data. Fuzzy logic learning algorithms satisfy the learning principles defined by the learning theory for neural networks. The learning principles not only require the algorithm to design and train the net in polynomial time, but attempts to generate the smallest possible net which attempts to generate the smallest set of fuzzy rules to describe the phenomenon. It implies generalization in learning and polynomial time complexity of learning algorithms.

AB - Fuzzy logic, neural network architectures and learning are integrated and unified. Learning fuzzy rules from data, may it be for classification or function approximation, are the same with training radial basis function (RBF) networks from the same data. Fuzzy logic learning algorithms satisfy the learning principles defined by the learning theory for neural networks. The learning principles not only require the algorithm to design and train the net in polynomial time, but attempts to generate the smallest possible net which attempts to generate the smallest set of fuzzy rules to describe the phenomenon. It implies generalization in learning and polynomial time complexity of learning algorithms.

UR - http://www.scopus.com/inward/record.url?scp=0030658512&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0030658512&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0030658512

VL - 1

SP - 522

EP - 527

BT - IEEE International Conference on Neural Networks - Conference Proceedings

PB - IEEE

CY - Piscataway, NJ, United States

ER -