## Abstract

Neural networks are successfully used to determine small particle properties from knowledge of the scattered light - an inverse light scattering problem. This type of problem is inherently difficult to solve as it is represented by a highly Ill-posed function mapping. This paper presents a technique that solves the inverse light scattering problem for spheres using Radial Basis Function (RBF) neural networks. A two-stage network architecture is arranged to enhance network approximation capability. In addition, a new approach to computing basis function parameters with respect to the inverse scattering problem is demonstrated The technique is evaluated for noise-free data through simulations, in which a minimum 99.06% approximation accuracy is achieved. A comparison is made between the least square and the orthogonal least square training methods.

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

Pages (from-to) | 177-186 |

Number of pages | 10 |

Journal | Neural Computing and Applications |

Volume | 8 |

Issue number | 2 |

DOIs | |

Publication status | Published - 1999 |

## Keywords

- basis function widths
- function approximation
- inverse light scattering problem
- Radial Basis Function neural networks
- small particles