Scientific Understanding of Consciousness
Visual System Learning via Statistics of Natural Scenes
Nature 457, 83-86 (1 January 2009)
Emergence of complex cell properties by learning to generalize in natural scenes
Yan Karklin & Michael S. Lewicki
Computer Science Department & Center for the Neural Basis of Cognition, Carnegie Mellon University, Pittsburgh, PA 15213, USA
Present address: Center for Neural Science, New York University, New York, New York, USA (Y.K.); Electrical Engineering and Computer Science Department, Case Western University, Cleveland, Ohio, USA and Wissenschaftskolleg (Institute for Advanced Study) zu Berlin, Germany (M.S.L.).
A fundamental function of the visual system is to encode the building blocks of natural scenes—edges, textures and shapes—that subserve visual tasks such as object recognition and scene understanding. Essential to this process is the formation of abstract representations that generalize from specific instances of visual input.
A common view holds that neurons in the early visual system signal conjunctions of image features, but how these produce invariant representations is poorly understood.
Here we propose that to generalize over similar images, higher-level visual neurons encode statistical variations that characterize local image regions.
We present a model in which neural activity encodes the probability distribution most consistent with a given image. Trained on natural images, the model generalizes by learning a compact set of dictionary elements for image distributions typically encountered in natural scenes. Model neurons show a diverse range of properties observed in cortical cells.
[end of paraphrase]
Return to — Vision