期刊
NEUROCOMPUTING
卷 47, 期 -, 页码 119-143出版社
ELSEVIER SCIENCE BV
DOI: 10.1016/S0925-2312(01)00583-5
关键词
unsupervised; multiple cause; sparse code
We define a minimum overcomplete basis as that set of basis vectors which has more members than necessary to span the space but which minimises an energy function of the space. We present an unsupervised artificial neural network that may be used to identify a minimum overcomplete basis for a data set. Building on a network which normally finds the principal components of data we have previously shown that, by applying a non-linearity which half-wave rectifies the outputs of this network, a much sparser response is achieved. The restriction of the coding to positive values necessitates an overcomplete representation. By adding Gaussian noise to the outputs after this rectification we may control the dimensionality of the overcomplete basis so that a minimal basis set is formed under the positive coding constraint. The operation of the network is demonstrated by the application of the network to artificial and natural image data. (C) 2002 Elsevier Science B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据