Matrix Variate RBM Model with Gaussian Distributions

TL;DR

This paper introduces a Matrix variate Gaussian RBM that effectively models multi-dimensional real-valued data, preserving data structure and improving image classification performance.

Contribution

It proposes a novel MVGRBM model for matrix data with Gaussian distributions, addressing limitations of traditional RBMs on real-valued, multi-dimensional data.

Findings

Better modeling of real-valued matrix data.

Improved image classification results.

Preserves data structure compared to vectorization.

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.