Presentation | 2013-12-21 Limited General Regression Neural Network for Embedded Systems and its quick calculation algorithm using a search tree Akihisa KATO, Koichiro YAMAUCHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recent improvement of the microcomputer enables the execution of complex intelligent algorithms on embedded systems. But, in the case of using a usual incremental learning method, its resource is often increased with learning , so that it is hard to continue to execute the incremental learning on small embedded systems. One of the author has already proposed a Limited General Regression Neural Network (LGRNN) for such limited environments. LGRNN continues incremental learning within a certain number of kernels with maintaining its flexibility, by replacing the most redundant kernel with a new kernel which records current new sample. In this study, we improved the LGRNN to reduce its computational complexity. Specifically, the improved LGRNN reduces the number of kernels to be calculated. Therefore, LGRNN calculates only k nearest kernels of current input. Moreover, the improved one searches such kernels quickly by using a tree search algorithm. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | |
Paper # | NC2013-66 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2013/12/14(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) | Limited General Regression Neural Network for Embedded Systems and its quick calculation algorithm using a search tree |
Sub Title (in English) | |
Keyword(1) | |
1st Author's Name | Akihisa KATO |
1st Author's Affiliation | Chubu University Department of Information Science() |
2nd Author's Name | Koichiro YAMAUCHI |
2nd Author's Affiliation | Chubu University Department of Information Science |
Date | 2013-12-21 |
Paper # | NC2013-66 |
Volume (vol) | vol.113 |
Number (no) | 374 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |