抄録
New algorithms for joint learning of independent component analysis and graphical high-order correlation (GC-ICA: Graphically Correlated ICA) are presented. The presented method has a fixed point style or of the FastICA, however, it comprises independent but correlated subparts. Correlations by teacher signals are also allowed. In spite of such inclusion of the dependency, the presented algorithm shows fast convergence. The converged set of bases has reduced indeterminacy on the ordering. This is equivalent to a self-organization of bases. This method can be used to analyze multiple images simultaneously. Examples are given on images from 3D- stereo videos shots. The correlation of bases on left and right eye views is shown for the first time here. Further speedup using the strategy of the RapidICA is possible.
本文言語 | English |
---|---|
ホスト出版物のタイトル | Proceedings of the International Joint Conference on Neural Networks |
ページ | 701-708 |
ページ数 | 8 |
DOI | |
出版ステータス | Published - 2011 |
イベント | 2011 International Joint Conference on Neural Network, IJCNN 2011 - San Jose, CA 継続期間: 2011 7月 31 → 2011 8月 5 |
Other
Other | 2011 International Joint Conference on Neural Network, IJCNN 2011 |
---|---|
City | San Jose, CA |
Period | 11/7/31 → 11/8/5 |
ASJC Scopus subject areas
- ソフトウェア
- 人工知能