Presentation | 2005/4/8 An Approach to Artificial Neural Networks as Multistage Threshold Networks : The Properties and an Exact Design Methodology Kiyoshi Furuya, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Properties of ANN's as multistage threshold networks are considered. Then an exact design methodology of ANN's is presented using pattern recognition problem of 20 patters (alphabets A-T) as an example. A method to attain certain level of fault-tolerance is also described. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | ANN(Artificial Neural Network) / threshold networks / pattern recognition problem |
Paper # | CPSY2005-6,DC2005-6 |
Date of Issue |
Conference Information | |
Committee | DC |
---|---|
Conference Date | 2005/4/8(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 | Dependable Computing (DC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | An Approach to Artificial Neural Networks as Multistage Threshold Networks : The Properties and an Exact Design Methodology |
Sub Title (in English) | |
Keyword(1) | ANN(Artificial Neural Network) |
Keyword(2) | threshold networks |
Keyword(3) | pattern recognition problem |
1st Author's Name | Kiyoshi Furuya |
1st Author's Affiliation | Faculty of Science and Engineering, CHuo University() |
Date | 2005/4/8 |
Paper # | CPSY2005-6,DC2005-6 |
Volume (vol) | vol.105 |
Number (no) | 4 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |