|
自然图像中学习高阶特征的一个因子模型
A Factor Model for Learning Higher Order Features in Natural Images |
|
| |
| 课程网址: |
http://videolectures.net/icml09_karklin_fmlh/
|
| 主讲教师: |
Yan Karklin
|
| 开课单位: |
纽约大学
|
| 开课时间: |
2009-08-26
|
| 课程语种: |
英语
|
| 中文简介: |
可视系统是处理阶段的层次结构。这条路径中的每个阶段，除了编码日益复杂的输入特征外，还执行复杂的非线性计算。这些非线性行为的功能作用是什么？我们如何将它们纳入自然图像的生成模型中？从自然图像中观察到的统计依赖性可以预测视觉神经元的一些非线性特性。例如，线性滤波器输出的大小是相关的；归一化滤波器响应消除了这种相关性（使响应更为独立且稍微高斯化），并重现了神经增益控制。此外，这些相关性中的模式本身信息量很大，可以用来推断从大场景中采样的补丁的上下文。在这里，我将重点介绍这些统计模式，并描述一个生成模型，该模型使用多元高斯分布的对数协方差空间中的一组因子捕获它们。在自然图像的训练下，该模型学习一个紧凑的代码，用于在像素（或线性特征）分布中观察到的相关性，这些分布代表图像的更抽象的特性。我还将把这项工作与最近的生成模型联系起来，后者包含观察变量和潜在变量之间的乘法交互。
|
| 课程简介: |
The visual system is a hierarchy of processing stages. Each stage in this pathway, in addition to encoding increasingly complex features of the input, performs complex non-linear computations. What is the functional role of these non-linear behaviors and how do we incorporate them into generative models of natural images? A number of non-linear properties of visual neurons can be predicted from the statistical dependencies observed in natural images. For example, the magnitudes of linear filter outputs are correlated; normalizing filter responses removes this correlation (making the responses more independent and marginally Gaussian) and reproduces neural gain control. In addition, the pattern in these correlations is itself highly informative, and can be used to infer the context of patches sampled from a large scene. Here I will focus on these statistical patterns and describe a generative model that captures them using a set of factors in the space of log-covariance of a multivariate Gaussian distribution. Trained on natural images, the model learns a compact code for correlations observed in pixel (or linear feature) distributions that represents more abstract properties of the image. I will also connect this work to recent generative models that incorporate multiplicative interactions between observed and latent variables.
|
| 关 键 词: |
非线性计算; 视觉神经元; 对数协方差; 多元高斯分布
|
| 课程来源: |
视频讲座网
|
| 最后编审: |
2019-12-07：lxf
|
| 阅读次数: |
50
|
|
图 书 馆