Abstract | ||
---|---|---|
The locally linear embedding (LLE) algorithm belongs to a group of manifold learning methods that not only merely reduce data dimensionality, but also attempt to discover a true low dimensional structure of the data. In this paper, we propose an incremental version of LLE and experimentally demonstrate its advantages in terms of topology preservation. Also compared to the original (batch) LLE, the incremental LLE needs to solve a much smaller optimization problem. |
Year | DOI | Venue |
---|---|---|
2005 | 10.1016/j.patcog.2005.04.006 | Pattern Recognition |
Keywords | Field | DocType |
Dimensionality reduction,LLE,Online mapping,Topology preservation | Embedding,Dimensionality reduction,Pattern recognition,Curse of dimensionality,Artificial intelligence,Nonlinear dimensionality reduction,Optimization problem,Machine learning,Mathematics | Journal |
Volume | Issue | ISSN |
38 | 10 | 0031-3203 |
Citations | PageRank | References |
39 | 1.76 | 1 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Olga Kouropteva | 1 | 210 | 18.87 |
Oleg Okun | 2 | 308 | 28.56 |
Matti Pietikäinen | 3 | 14779 | 739.80 |