Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statistics
This provides insights for researchers in machine learning and computer vision working with density models and natural image analysis, but it is incremental as it builds on existing GRBM frameworks.
The paper tackled the problem of understanding and training Gaussian-binary restricted Boltzmann machines (GRBMs) for modeling natural image statistics, showing that GRBMs can learn meaningful features and that training difficulties are due to algorithmic failures rather than the model itself, with proposed recipes enabling successful and fast training.
We present a theoretical analysis of Gaussian-binary restricted Boltzmann machines (GRBMs) from the perspective of density models. The key aspect of this analysis is to show that GRBMs can be formulated as a constrained mixture of Gaussians, which gives a much better insight into the model's capabilities and limitations. We show that GRBMs are capable of learning meaningful features both in a two-dimensional blind source separation task and in modeling natural images. Further, we show that reported difficulties in training GRBMs are due to the failure of the training algorithm rather than the model itself. Based on our analysis we are able to propose several training recipes, which allowed successful and fast training in our experiments. Finally, we discuss the relationship of GRBMs to several modifications that have been proposed to improve the model.