### Abstract

In this paper, we propose a new method for inverting feedforward neural networks. Inversion of neural networks means to find the inputs which produce given outputs. In general, this is an ill-posed problem whose solution isn't unique. Inversion using iterative optimization method (for example gradient descent, quasi-Newton method) is useful to this problem and it is called "iterative inversion". We propose a new iterative inversion using a Bottleneck Neural Network with Hidden layer's input units (BNNH), which we design on the basis of Bottleneck Neural Network (BNN). Compressing input space by BNNH, we reduce the dimension of search space, or input space to be searched with iterative inversion. With reduction of the search space's dimension, performance about computation time and accuracy is expected to become better. In experiments, the proposed method is applied to some examples. These results show the effectively of the proposed method.

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

Title of host publication | Proceedings of the IEEE International Conference on Systems, Man and Cybernetics |

Pages | 1612-1617 |

Number of pages | 6 |

Volume | 2 |

Publication status | Published - 2003 |

Event | System Security and Assurance - Washington, DC, United States Duration: 2003 Oct 5 → 2003 Oct 8 |

### Other

Other | System Security and Assurance |
---|---|

Country | United States |

City | Washington, DC |

Period | 03/10/5 → 03/10/8 |

### Fingerprint

### Keywords

- Bottleneck neural networks
- Ill-posed problem
- Inverse problem
- Iterative optimization method

### ASJC Scopus subject areas

- Hardware and Architecture
- Control and Systems Engineering

### Cite this

*Proceedings of the IEEE International Conference on Systems, Man and Cybernetics*(Vol. 2, pp. 1612-1617)

**A new method for inverting feedforward neural networks.** / Araki, Yoshio; Ohki, Toshifumi; Citterio, Daniel; Hagiwara, Masafumi; Suzuki, Koji.

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

*Proceedings of the IEEE International Conference on Systems, Man and Cybernetics.*vol. 2, pp. 1612-1617, System Security and Assurance, Washington, DC, United States, 03/10/5.

}

TY - GEN

T1 - A new method for inverting feedforward neural networks

AU - Araki, Yoshio

AU - Ohki, Toshifumi

AU - Citterio, Daniel

AU - Hagiwara, Masafumi

AU - Suzuki, Koji

PY - 2003

Y1 - 2003

N2 - In this paper, we propose a new method for inverting feedforward neural networks. Inversion of neural networks means to find the inputs which produce given outputs. In general, this is an ill-posed problem whose solution isn't unique. Inversion using iterative optimization method (for example gradient descent, quasi-Newton method) is useful to this problem and it is called "iterative inversion". We propose a new iterative inversion using a Bottleneck Neural Network with Hidden layer's input units (BNNH), which we design on the basis of Bottleneck Neural Network (BNN). Compressing input space by BNNH, we reduce the dimension of search space, or input space to be searched with iterative inversion. With reduction of the search space's dimension, performance about computation time and accuracy is expected to become better. In experiments, the proposed method is applied to some examples. These results show the effectively of the proposed method.

AB - In this paper, we propose a new method for inverting feedforward neural networks. Inversion of neural networks means to find the inputs which produce given outputs. In general, this is an ill-posed problem whose solution isn't unique. Inversion using iterative optimization method (for example gradient descent, quasi-Newton method) is useful to this problem and it is called "iterative inversion". We propose a new iterative inversion using a Bottleneck Neural Network with Hidden layer's input units (BNNH), which we design on the basis of Bottleneck Neural Network (BNN). Compressing input space by BNNH, we reduce the dimension of search space, or input space to be searched with iterative inversion. With reduction of the search space's dimension, performance about computation time and accuracy is expected to become better. In experiments, the proposed method is applied to some examples. These results show the effectively of the proposed method.

KW - Bottleneck neural networks

KW - Ill-posed problem

KW - Inverse problem

KW - Iterative optimization method

UR - http://www.scopus.com/inward/record.url?scp=0242660370&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0242660370&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0242660370

VL - 2

SP - 1612

EP - 1617

BT - Proceedings of the IEEE International Conference on Systems, Man and Cybernetics

ER -