Matrix Variate RBM Model with Gaussian Distributions

2016/09/21 by Simeng Liu, Yanfeng Sun, Liu, Simeng +7
Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #cs.CV

paper · pdf · doi:10.48550/arxiv.1609.06417

We think we need more mathematical derivation and experiments to support the proposed theory of the paper. In this period, it is not appropriate to publish it

arxiv created 2016/09/27 · arxiv updated 2016/09/28

Abstract

Restricted Boltzmann Machine (RBM) is a particular type of random neural network models modeling vector data based on the assumption of Bernoulli distribution. For multi-dimensional and non-binary data, it is necessary to vectorize and discretize the information in order to apply the conventional RBM. It is well-known that vectorization would destroy internal structure of data, and the binary units will limit the applying performance due to fickle real data. To address the issue, this paper proposes a Matrix variate Gaussian Restricted Boltzmann Machine (MVGRBM) model for matrix data whose entries follow Gaussian distributions. Compared with some other RBM algorithm, MVGRBM can model real value data better and it has good performance in image classification.

Related

• Matrix Variate RBM and Its Applications
• Reformulation of RBM to Unify Linear and Nonlinear Dimensionality Reduction
• Tractable loss function and color image generation of multinary restricted Boltzmann machine
• Learning Gaussian-Bernoulli RBMs using Difference of Convex Functions Optimization
• Efficient Learning of Restricted Boltzmann Machines Using Covariance Estimates