TY - JOUR

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 - 2003/11/24

Y1 - 2003/11/24

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 article

AN - SCOPUS:0242660370

VL - 2

SP - 1612

EP - 1617

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

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

SN - 0884-3627

T2 - System Security and Assurance

Y2 - 5 October 2003 through 8 October 2003

ER -