Presentation | 1997/6/19 Visual Learnign and Prediction of Motion Patterns Tadashi Ogawa, Hiroshi Ando, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | We studied Elman-type recurrent neural networks for predicting and classifying spatio-temporal visual patterns. Computer experiments, using the complex temporal data of human arm movements, demonstrated that the network model has the following abilities; 1)short-term prediction, 2)long-term prediction, 3)motion pattern classification, 4)view generalization, 5)learning multiple patterns from different, viewpoints, and 6)temporal adaptation for time scaling. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | recurrent neural networks / view generalization / spatio-temporal prediction / motion pattern classification / temporal adaptation |
Paper # | NC97-22 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1997/6/19(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) | Visual Learnign and Prediction of Motion Patterns |
Sub Title (in English) | |
Keyword(1) | recurrent neural networks |
Keyword(2) | view generalization |
Keyword(3) | spatio-temporal prediction |
Keyword(4) | motion pattern classification |
Keyword(5) | temporal adaptation |
1st Author's Name | Tadashi Ogawa |
1st Author's Affiliation | Graduate School of Information Science, Nara Institute of Science and Technology() |
2nd Author's Name | Hiroshi Ando |
2nd Author's Affiliation | ATR Human Information Processing Research Laboratories |
Date | 1997/6/19 |
Paper # | NC97-22 |
Volume (vol) | vol.97 |
Number (no) | 116 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |