Abstract | ||
---|---|---|
We present a method that uses competitive learning and a neighbourhood function in a similar way to the self-organising map (SOM) (3). The network consists of a number of modules that are positioned in an array (normally in one or two dimensions) where each module performs a subspace projection and the rotation of these subspaces is weighted b y the neighbourhood function. Non-linear activation functions are introduced so that each node performs non- linear PCA on the training data captured in its Voronoi region. We show that this network may be used for position invariant detection of bars at varying orientations. |
Year | Venue | Keywords |
---|---|---|
1998 | ESANN | competitive learning,two dimensions,activation function,data capture |
Field | DocType | Citations |
Computer vision,Invariant feature,Pattern recognition,Computer science,Artificial intelligence,Machine learning | Conference | 1 |
PageRank | References | Authors |
0.43 | 3 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Stephen Mcglinchey | 1 | 9 | 2.94 |
Colin Fyfe | 2 | 508 | 55.62 |