Presentation | 1997/11/17 A Learning Algorithm for Improvement of Compression Ability by Multi-Layered Neural Networks Eiji Watanabe, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this report, a learning algorithm for improvement of compression ability by multi-layered neural networks (NNs). It is known that we can the compressed information in the hidden layer, when input patterns are identical with output patterns. However, it needs many hidden units and many learning iterations in the image compression. Moreover, when the original image has complex patterns, single NN model can not decode such a image with high accuracy. Accordingly, this report proposes learning algorithms for the segmentation and the quantitization of image. Finally, the compression rate and the decoding performance for a image are discussed in detail. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Multi-layered neural network / Data compression / Gray image / Segmentation / Quantitization |
Paper # | NC97-50 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1997/11/17(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 Learning Algorithm for Improvement of Compression Ability by Multi-Layered Neural Networks |
Sub Title (in English) | |
Keyword(1) | Multi-layered neural network |
Keyword(2) | Data compression |
Keyword(3) | Gray image |
Keyword(4) | Segmentation |
Keyword(5) | Quantitization |
1st Author's Name | Eiji Watanabe |
1st Author's Affiliation | Department of Information Processing Engineering Faculty of Engineering, Fukuyama University() |
Date | 1997/11/17 |
Paper # | NC97-50 |
Volume (vol) | vol.97 |
Number (no) | 379 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |