Sparse coding of natural contours

Sparse coding of natural contours
复制标题

DOI:
10.1016/s0925-2312(02)00400-9
复制
发表时间:
2002-06-01
期刊:
影响因子:
6
通讯作者:
Hyvärinen, A
Hyvärinen, A
中科院分区:
计算机科学2区
文献类型:
--
作者:
Hoyer, PO;Hyvärinen, A

文献摘要

被引文献

相似文献

视觉神经科学中的一个重要方法是考虑早期视觉系统的功能如何与其自然输入的统计数据相关。以前的工作已经表明,经典的感受野和初级视觉皮层的组织(地形)可以被视为有效的编码自然图像。在这里,我们通过考虑如何通过高阶神经层有效地编码复杂细胞的响应来扩展框架。这导致了自然图像中轮廓的稀疏编码,并且可以解释感受野的某些超经典特性。(C)2002 Elsevier Science B.V.保留所有权利。
An important approach in visual neuroscience considers how the function of the early visual system relates to the statistics of its natural input. Previous work has shown how the classical receptive fields and the organization (topography) of the primary visual cortex can be viewed as efficient coding of natural images. Here, we extend the framework by considering how the responses of complex cells could be efficiently coded by a higher-order neural layer. This leads to the sparse coding of contours in natural images, and can explain certain extra-classical properties of receptive fields. (C) 2002 Elsevier Science B.V. All rights reserved.