Presentation | 2005-07-30 Medical Image Recognition by self-selecting algorithm for optimum neural network architecture Tadashi Kondo, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this study, medical image recognition by self-selecting algorithm for optimum neural network architecture is developed. This algorithm is call as the GMDH-type neural network with sigmoid functions. The GMDH-type neural network algorithm with sigmoid functions can automatically generate the optimum neural network architecture that fits the complexity of the nonlinear system. The structural parameters such as the number of the layers, the number of the neurons in the hidden layers, the useful input variables are automatically determined so as to minimize the error criterion defined as AIC (Akaike's information criterion). Therefore, it is very easy to apply the GMDH-type neural network with sigmoid functions to the medical image recognition. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | GMDH / Neural Network / Medical Image Recognition |
Paper # | MBE2005-52 |
Date of Issue |
Conference Information | |
Committee | MBE |
---|---|
Conference Date | 2005/7/23(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 | ME and Bio Cybernetics (MBE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Medical Image Recognition by self-selecting algorithm for optimum neural network architecture |
Sub Title (in English) | |
Keyword(1) | GMDH |
Keyword(2) | Neural Network |
Keyword(3) | Medical Image Recognition |
1st Author's Name | Tadashi Kondo |
1st Author's Affiliation | University of Tokushima() |
Date | 2005-07-30 |
Paper # | MBE2005-52 |
Volume (vol) | vol.105 |
Number (no) | 222 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |