Presentation | 1999/6/9 Compression of Time Series With Recurrent Newral Network Atsushi MATSUNO, Yoshikazu MIYANAGA, Kouji TOCHINAI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | A recurrent neural network has been already recognized as a suitable method for the efficient processing of time series. However, the network requires a large number of links with weights and thus the design size and its training time become quit large and long. This report introduces an optimum method of network size suitable for given time series. It results on short training time and lower calicuration cost. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Recurrent Newral Network / Structure optimizing / Time Series |
Paper # | VLD99-9 |
Date of Issue |
Conference Information | |
Committee | VLD |
---|---|
Conference Date | 1999/6/9(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 | VLSI Design Technologies (VLD) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Compression of Time Series With Recurrent Newral Network |
Sub Title (in English) | |
Keyword(1) | Recurrent Newral Network |
Keyword(2) | Structure optimizing |
Keyword(3) | Time Series |
1st Author's Name | Atsushi MATSUNO |
1st Author's Affiliation | Graduate school of Engineering, Hokkaido University() |
2nd Author's Name | Yoshikazu MIYANAGA |
2nd Author's Affiliation | Graduate school of Engineering, Hokkaido University |
3rd Author's Name | Kouji TOCHINAI |
3rd Author's Affiliation | Graduate school of Engineering, Hokkaido University |
Date | 1999/6/9 |
Paper # | VLD99-9 |
Volume (vol) | vol.99 |
Number (no) | 106 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |