| Presentation | 1996/6/21 A neural networks approach to inverse optimization problems with nonstandard quadratic criterion functions Hong Zhang, Masumi Ishikawa, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Proposed in this paper is a novel neural networks approach to inverse optimization problems with nonstandard quadratic criterion functions. An inverse optimization problem here means to obtain a positive semidefinite quadratic criterion function which makes a given solution optimal under given constraint conditions. However, in contrast to the case of standard quadratic criterion functions, a criterion function cannot be determined uniquely even when there is only one active constraint condition. To solve this difficulty, it is proposed to obtain a criterion function closest to the standard quadratic criterion function. For this purpose, the sum of the absolute values of off-diagonal connection weights and that of squares of them are used as indicators for the distance form the standard quadratic criterion function. A structural learning with forgetting applied to off diagonal connection weights successfully generates a simplified quadratic criterion function. How criterion parameters and Lagrange multipliers changes for various gradient vectors is also analyzed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | inverse optimization problem / neural network / nonstandard quadratic optimization / structural learning with forgetting |
| Paper # | NC96-15 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 1996/6/21(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Neurocomputing (NC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | A neural networks approach to inverse optimization problems with nonstandard quadratic criterion functions |
| Sub Title (in English) | |
| Keyword(1) | inverse optimization problem |
| Keyword(2) | neural network |
| Keyword(3) | nonstandard quadratic optimization |
| Keyword(4) | structural learning with forgetting |
| 1st Author's Name | Hong Zhang |
| 1st Author's Affiliation | Kyushu Institute of Technology() |
| 2nd Author's Name | Masumi Ishikawa |
| 2nd Author's Affiliation | Kyushu Institute of Technology |
| Date | 1996/6/21 |
| Paper # | NC96-15 |
| Volume (vol) | vol.96 |
| Number (no) | 117 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |