Abstract | ||
---|---|---|
Locally linear embedding(LLE) is a typical manifold learning algorithms. Aim to the difficulty of selecting neighborhood parameter on the algorithm, a neighborhood parameter optimization method based on topology preservation is developed in the paper. From the point of the dimension reduction mapping quality, the error function of topology preservation is constructed to keep mapping quality. The optimization of the neighborhood is obtained according to the minimum of the error function. The experimental results on IRIS validate the optimization of the neighborhood and the effectiveness of feature distribution. © 2011 IEEE. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/EMEIT.2011.6023107 | EMEIT |
Keywords | Field | DocType |
lle,neighborhood optimization,topology preservation,learning artificial intelligence,graph theory,parameter estimation | Graph theory,Error function,Topology,Mathematical optimization,Dimensionality reduction,Embedding,Topology optimization,Estimation theory,Nonlinear dimensionality reduction,Mathematics | Conference |
Volume | Issue | Citations |
8 | null | 0 |
PageRank | References | Authors |
0.34 | 1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Quansheng Jiang | 1 | 2 | 1.40 |
Yepin Lu | 2 | 0 | 0.34 |
Zuokui Hong | 3 | 0 | 0.34 |