论文信息 - Comparative Analysis of Residual Minimization and Artificial Neural Networks as Methods of Solving Inverse Problems: Test on Model Data

Comparative Analysis of Residual Minimization and Artificial Neural Networks as Methods of Solving Inverse Problems: Test on Model Data

This study compares perceptron type neural network and residual minimization for solving inverse problems, at the example of a model inverse problem. Stability of both methods against noise in data was investigated. The conclusion about limited applicability of residual as a criterion of the solution quality has been made.

Sergey Dolenko | Igor Isaev | S. Dolenko | I. Isaev

[1] I. G. Persiantsev,et al. Study of Influence of Parameter Grouping on the Error of Neural Network Solution of the Inverse Problem of Electrical Prospecting , 2013, EANN.

[2] V. Spichak,et al. Artificial neural network inversion of magnetotelluric data in terms of three‐dimensional earth macroparameters , 2000 .

[3] Haitian Yang,et al. Solving inverse bimodular problems via artificial neural network , 2009 .

[4] Brijesh Verma,et al. RBF neural networks for solving the inverse problem of backscattering spectra , 2008, Neural Computing and Applications.

[5] Michael S. Zhdanov,et al. Geophysical Electromagnetic Theory and Methods , 2009 .