| Presentation | 2008-05-23 Experimental Study for Dominance to Accuracy of Prediction Output of Parallel-type Neuron Network Shunsuke KOBAYAKAWA, Hirokazu YOKOI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The parallel-type neuron network (PNN) is researched to improve on the decrease in the ability on the neuron network by the interference of the learning caused between the outputs of BP network (BPN) more than two outputs and the difficulty of the common achievement of the middle layer used for the each output. The research to compare prediction accuracies with nonlinear time series signal prediction systems used BPN and PNN had been performed so far, but it had not arrived at proving to the existence of dominance of accuracy of all prediction outputs of PNN to BPN. Then, the experimental study of the dominance of all outputs of PNN which could exist for the theory by results of the comparison of learning rules of BPN and PNN was performed using nonlinear time series signal prediction systems in this research. As the results, it showed to obtain the dominance almost. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Parallel-type Neuron Network / BP Network / Nonlinear Time Series Signal Prediction System / Prediction Accuracy / Learning Rule |
| Paper # | NC2008-6 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2008/5/16(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) | Experimental Study for Dominance to Accuracy of Prediction Output of Parallel-type Neuron Network |
| Sub Title (in English) | |
| Keyword(1) | Parallel-type Neuron Network |
| Keyword(2) | BP Network |
| Keyword(3) | Nonlinear Time Series Signal Prediction System |
| Keyword(4) | Prediction Accuracy |
| Keyword(5) | Learning Rule |
| 1st Author's Name | Shunsuke KOBAYAKAWA |
| 1st Author's Affiliation | Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology() |
| 2nd Author's Name | Hirokazu YOKOI |
| 2nd Author's Affiliation | Graduate School of Life Science and Systems Engineering, Kyushu Institute of Technology |
| Date | 2008-05-23 |
| Paper # | NC2008-6 |
| Volume (vol) | vol.108 |
| Number (no) | 54 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |