efficient sparse coding in early sensory processing lessons from signal recovery有效的稀疏编码在早期的感觉处理教训信号恢复.pdfVIP

Efficient Sparse Coding in Early Sensory Processing: Lessons from Signal Recovery ´ ¨ 1 2,3 ´ 1,4 Andras Lorincz *, Zsolt Palotai , Gabor Szirtes ¨ ¨ ´ 1 Department of Software Technology and Methodology, Eotvos Lorand University, Budapest, Hungary, 2 Sparsense Inc., Boca Raton, Florida, United States of America, 3 ELTE-Soft Ltd, Budapest, Hungary, 4 Center for Integrative Neuroscience, University of Tuebingen, Tuebingen, Germany Abstract Sensory representations are not only sparse, but often overcomplete: coding units significantly outnumber the input units. For models of neural coding this overcompleteness poses a computational challenge for shaping the signal processing channels as well as for using the large and sparse representations in an efficient way. We argue that higher level overcompleteness becomes computationally tractable by imposing sparsity on synaptic activity and we also show that such structural sparsity can be facilitated by statistics based decomposition of the stimuli into typical and atypical parts prior to sparse coding. Typical parts represent large-scale correlations, thus they can be significantly compressed. Atypical parts, on the other hand, represent local features and are the subjects of actual sparse coding. When applied on natural images, our decomposition based sparse coding model can efficiently form overcomplete codes and both center-surround and oriented filters are obtained similar to those observed in the retina and the primary visual cortex, respectively. Therefore we hypothesize that the proposed computational architecture can be seen as a coherent functional model of the first stages of sensory coding in ea