### Abstract

It is widely acknowledged that in principle a potentially infinitely large neural network (either in number of neurons or in the precision of a single neural activity) could possess an equivalent computational power as a Turing machine. In the present work, the authors show such an equivalence of Turing machines to several explicitly constructed neural networks. It is proven that for any given Turing machine there exists a recurrent neural network with local, second-order, and uniformly connected weights (i.e., the weights connecting the second-order product of local 'input neurons' with their corresponding 'output neurons') which can simulate it. The numerical implementation and learning of such a neural Turing machine are also discussed.

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

Title of host publication | Proceedings. IJCNN - International Joint Conference on Neural Networks |

Editors | Anon |

Publisher | Publ by IEEE |

Pages | 357-362 |

Number of pages | 6 |

ISBN (Print) | 0780301641 |

State | Published - Jan 1 1992 |

Event | International Joint Conference on Neural Networks - IJCNN-91-Seattle - Seattle, WA, USA Duration: Jul 8 1991 → Jul 12 1991 |

### Publication series

Name | Proceedings. IJCNN - International Joint Conference on Neural Networks |
---|

### Other

Other | International Joint Conference on Neural Networks - IJCNN-91-Seattle |
---|---|

City | Seattle, WA, USA |

Period | 7/8/91 → 7/12/91 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Engineering(all)

### Cite this

*Proceedings. IJCNN - International Joint Conference on Neural Networks*(pp. 357-362). (Proceedings. IJCNN - International Joint Conference on Neural Networks). Publ by IEEE.

}

*Proceedings. IJCNN - International Joint Conference on Neural Networks.*Proceedings. IJCNN - International Joint Conference on Neural Networks, Publ by IEEE, pp. 357-362, International Joint Conference on Neural Networks - IJCNN-91-Seattle, Seattle, WA, USA, 7/8/91.

**Turing equivalence of neural networks with second order connection weights.** / Sun, Guo Zheng; Chen, Hsing Hen; Lee, Yee Chun; Giles, C. Lee.

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

TY - GEN

T1 - Turing equivalence of neural networks with second order connection weights

AU - Sun, Guo Zheng

AU - Chen, Hsing Hen

AU - Lee, Yee Chun

AU - Giles, C. Lee

PY - 1992/1/1

Y1 - 1992/1/1

N2 - It is widely acknowledged that in principle a potentially infinitely large neural network (either in number of neurons or in the precision of a single neural activity) could possess an equivalent computational power as a Turing machine. In the present work, the authors show such an equivalence of Turing machines to several explicitly constructed neural networks. It is proven that for any given Turing machine there exists a recurrent neural network with local, second-order, and uniformly connected weights (i.e., the weights connecting the second-order product of local 'input neurons' with their corresponding 'output neurons') which can simulate it. The numerical implementation and learning of such a neural Turing machine are also discussed.

AB - It is widely acknowledged that in principle a potentially infinitely large neural network (either in number of neurons or in the precision of a single neural activity) could possess an equivalent computational power as a Turing machine. In the present work, the authors show such an equivalence of Turing machines to several explicitly constructed neural networks. It is proven that for any given Turing machine there exists a recurrent neural network with local, second-order, and uniformly connected weights (i.e., the weights connecting the second-order product of local 'input neurons' with their corresponding 'output neurons') which can simulate it. The numerical implementation and learning of such a neural Turing machine are also discussed.

UR - http://www.scopus.com/inward/record.url?scp=0026715336&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026715336&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026715336

SN - 0780301641

T3 - Proceedings. IJCNN - International Joint Conference on Neural Networks

SP - 357

EP - 362

BT - Proceedings. IJCNN - International Joint Conference on Neural Networks

A2 - Anon, null

PB - Publ by IEEE

ER -