Matrix Variate RBM Model with Gaussian Distributions
This addresses the problem of data structure loss and performance limitations in RBMs for researchers and practitioners in machine learning, particularly in image processing, but it is incremental as it extends existing RBM methods.
The paper tackled the limitation of conventional Restricted Boltzmann Machines (RBMs) in handling multi-dimensional, non-binary data by proposing a Matrix variate Gaussian RBM (MVGRBM) model for matrix data with Gaussian distributions, resulting in improved performance for real-value data and image classification.
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.