Learning to recognize objects

Evidence from neurophysiological and psychological studies is coming togeth er to shed light on how we represent and recognize objects. this review des cribes evidence supporting two major hypotheses: the first is that objects are represented in a mosaic-like form in which objects are encoded by combi nations of complex, reusable features. rather than two-dimensional template s, or three-dimensional models. the second hypothesis is that transform-inv ariant representations of objects are learnt through experience, and that t his learning is affected by the temporal sequence in which different views of the objects are seen, as well as by their physical appearance.