Learning of Neural Information Routing for Correspondence Finding
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Learning of lateral connections for representational invariant recognition
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part III
Self-organization of steerable topographic mappings as basis for translation invariance
ICANN'10 Proceedings of the 20th international conference on Artificial neural networks: Part II
A multifactor winner-take-all dynamics
Neural Computation
Self-organization of topographic bilinear networks for invariant recognition
Neural Computation
| Hi-index | 0.00 |
A viewpoint-independent description of the shape of an object can be generated by imposing a canonical frame of reference on the object and describing the spatial dispositions of the parts relative to this object-based frame. When a familiar object is in an unusual orientation, the deciding factor in the choice of the canonical object-based frame may be the fact that relative to this frame the object has a familiar shape description. This may suggest that we first hypothesise an object-based frame and then test the resultant shape description for familiarity. However, it is possible to organise the interactions between units in a parallel network so that the pattern of activity in the network simultaneously converges on a representation of the shape and a representation of the object-based frame of reference. The connections in the network are determined by the constraints inherent in the image formation process.