Independently varying companions can make an individual object’s features more consistently related than the features of any particular multi-object conjunction. Competitive networks can exploit this difference to learn separate object representations without being shown each object in isolation. The result depends on the training distribution; a fixed co-occurring group can instead be learned as a conjunction.[ref]
Invariant object recognition with trace learning and multiple stimuli present during training by Simon M. Stringer and others. Abstract; Network 18, pp. 161–187, changing object repertoire and trace learning with multiple objects
[ref]Learning transform invariant object recognition in the visual system with multiple stimuli present during training by Simon M. Stringer and others. Abstract; Neural networks 21, pp. 888–903, competitive networks and rotating 3D objects
Articles by others on the same topic
There are currently no matching articles.