Learning to represent spatial transformations with factored higher-order Boltzmann machinesWOSEI

摘要

To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicative interactions that use the intensity of a pixel in the first image as a multiplicative gain on a learned, symmetric weight between a pixel in the second image and a hidden unit. This creates cubically many parameters, which form a three-dimensional interaction tensor. We describe a low-rank approximation to this interaction tensor that uses a sum of factor...更多
个人信息

 

您的评分 :

Neural Computation, pp. 1473-1492, 2010.

被引用次数221|引用|18
标签
作者
评论