Abstract | ||
---|---|---|
This letter discusses blind separability based on temporal predictability (Stone, 2001 ; Xie, He, & Fu, 2005 ). Our results show that the sources are separable using the temporal predictability method if and only if they have different temporal structures (i.e., autocorrelations). Consequently, the applicability and limitations of the temporal predictability method are clarified. In addition, instead of using generalized eigendecomposition, we suggest using joint approximate diagonalization algorithms to improve the robustness of the method. A new criterion is presented to evaluate the separation results. Numerical simulations are performed to demonstrate the validity of the theoretical results. |
Year | DOI | Venue |
---|---|---|
2009 | 10.1162/neco.2009.10-08-890 | Neural Computation |
Keywords | Field | DocType |
theoretical result,new criterion,different temporal structure,temporal predictability,temporal predictability method,separation result,blind separability,joint approximate diagonalization algorithm,numerical simulation,generalized eigendecomposition | Predictability,Computer simulation,Separable space,Models of neural computation,Robustness (computer science),Artificial intelligence,Eigendecomposition of a matrix,Artificial neural network,Mathematics,Machine learning,Autocorrelation | Journal |
Volume | Issue | ISSN |
21 | 12 | 0899-7667 |
Citations | PageRank | References |
0 | 0.34 | 16 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shengli Xie | 1 | 2530 | 161.51 |
Guoxu Zhou | 2 | 908 | 41.46 |
Zu-yuan Yang | 3 | 312 | 24.12 |
Yuli Fu | 4 | 200 | 29.90 |