Learning transformation-tolerant representations by combining input-feature overlap, current-activity Hebbian learning and synaptic competition. A new view partly activates an output already learned for an overlapping view, then strengthens its new features onto that output. Chains of overlapping views can link more distant transformations without an explicit temporal trace; dense enough overlap and suitable competition remain conditions.[ref]
Learning invariant object recognition in the visual system with continuous transformations by Simon M. Stringer and others. Abstract and Introduction, pp. 128–131; experiments 3–4 distinguish spatial overlap from temporal ordering
Articles by others on the same topic
There are currently no matching articles.