Abstract | ||
---|---|---|
Possible application of a new neural network suitable for binary factorization of signals of large dimension and complexity is introduced. We developed the new recall pro- cedure of Hoppfield-like associative memory which allows search all attractors corresponding to factors (a true attrac- tor). Necessary separation of spurious attractors is based on calculation of their Lyapunov function. Being applied to textual data the procedure allows to reveal groups of highly correlated words (factors) which frequently occur in docu- ments jointly and represent topics of that documents. |
Year | Venue | Keywords |
---|---|---|
2005 | SITIS | lyapunov function,neural network,associative memory |
Field | DocType | Citations |
Nonlinear system,Pattern recognition,Computer science,Recurrent neural network,Probabilistic neural network,Time delay neural network,Artificial intelligence,Artificial neural network,Binary number | Conference | 5 |
PageRank | References | Authors |
0.83 | 2 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dusan Húsek | 1 | 60 | 11.37 |
Hana Rezanková | 2 | 56 | 9.79 |
Václav Snasel | 3 | 1261 | 210.53 |
Alexander A. Frolov | 4 | 180 | 29.31 |
Pavel Polyakov | 5 | 29 | 3.91 |