首页> 外文会议>Annual Computational Neuroscience Meeting(CNS'02); 20020721-20020725; Chicago,IL; US >A two-layer temporal generative model of natural video exhibits complex-cell-like pooling of simple cell outputs
【24h】

A two-layer temporal generative model of natural video exhibits complex-cell-like pooling of simple cell outputs

机译:自然视频的两层时间生成模型显示简单单元输出的类复杂单元池

获取原文
获取原文并翻译 | 示例

摘要

We present a two-layer dynamic generative model of the statistical structure of natural image sequences. The second layer of the model is a linear mapping from simple cell outputs to pixel values, as in most work on natural image statistics. The first layer models the dependencies of the activity levels (amplitudes or variances) of the simple cells, using a multivariate autoregressive model. The second layer shows emergence of basis vectors that are localized, oriented and have different scales, just like previous work. But our new model enables the first layer to learn connections between the simple cells that are similar to complex cell pooling: connections are strong among cells with similar location, frequency and orientation. In contrast to previous work in which one of the layers needed to be fixed in advance, the dynamic model enables us to estimate both of the layers simultaneously from natural data.
机译:我们提出了自然图像序列统计结构的两层动态生成模型。该模型的第二层是从简单像元输出到像素值的线性映射,就像大多数有关自然图像统计的工作一样。第一层使用多元自回归模型对简单单元的活动水平(幅度或方差)的依赖性进行建模。第二层显示基础向量的出现,这些基础向量是局部的,定向的并且具有不同的尺度,就像以前的工作一样。但是,我们的新模型使第一层能够学习类似于复杂单元池的简单单元之间的连接:位置,频率和方向相似的单元之间的连接牢固。与先前需要固定其中一层的先前工作相反,动态模型使我们能够从自然数据中同时估计这两层。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号