The ''independent components'' of natural scenes are edge filters
The ''independent components'' of natural scenes are edge filters
复制标题
DOI：
10.1016/s0042-6989(97)00121-1
复制
发表时间：
1997-12-01
期刊：
影响因子：
1.8
通讯作者：
Sejnowski, TJ
中科院分区：
文献类型：
--
作者：
Bell, AJ;Sejnowski, TJ
先前有人提出，在猫和猴子的初级视觉皮层中发现的具有线条和边缘选择性的神经元对自然场景形成了一种稀疏的分布式表征，并且有人推断，这种反应应该来自一种无监督学习算法，该算法试图找到独立视觉特征的因子编码。我们在此表明，一种基于信息最大化的新型无监督学习算法，即一个非线性的“信息最大化”网络，当应用于一组自然场景时，会产生局部化且有方向的视觉滤波器组。其中一些滤波器类似于加博尔滤波器，与稀疏最大化网络产生的滤波器相似。此外，由于这个信息最大化网络对稀疏（超高斯）分量分布执行独立成分分析（ICA），这些滤波器的输出尽可能相互独立。我们将由此产生的ICA滤波器及其相关基函数与主成分分析（PCA）产生的其他去相关滤波器以及零相位白化滤波器（ZCA）进行了比较。ICA滤波器在自然场景上具有更稀疏分布（峰态）的输出。它们也类似于视觉皮层中简单细胞的感受野，这表明这些神经元为自然图像形成了一个自然的、信息论的坐标系。（C）1997年爱思唯尔科学有限公司
It has previously been suggested that neurons with line and edge selectivities found in primary visual cortex of cats and monkeys form a sparse, distributed representation of natural scenes, and it has been reasoned that such responses should emerge from an unsupervised learning algorithm that attempts to find a factorial code of independent visual features, We show here that a new unsupervised learning algorithm based on information maximization, a nonlinear ''infomax'' network, when applied to an ensemble of natural scenes produces sets of visual filters that are localized and oriented, Some of these filters are Gabor-like and resemble those produced by the sparseness-maximization network. In addition, the outputs of these filters are as independent as possible, since this infomax network performs Independent Components Analysis or ICA, for sparse (super-gaussian) component distributions, We compare the resulting ICA filters and their associated basis functions, with other decorrelating filters produced by Principal Components Analysis (PCA) and zero-phase whitening filters (ZCA), The ICA filters have more sparsely distributed (kurtotic) outputs on natural scenes, They also resemble the receptive fields of simple cells in visual cortex, which suggests that these neurons form a natural, information-theoretic coordinate system for natural images. (C) 1997 Elsevier Science Ltd.