# Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statistics

arXiv: https://arxiv.org/abs/1401.5900 · HTML: https://mlsanity.com/paper/1401.5900/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Jan 2014.

## Built on by (most cited first, 7 of 7)

- [Gaussian-Bernoulli RBMs Without Tears](https://mlsanity.com/paper/2210.10318/) (2022)
- [On the mapping between Hopfield networks and Restricted Boltzmann Machines](https://mlsanity.com/paper/2101.11744/) (2021)
- [Using Perturbation to Improve Goodness-of-Fit Tests based on Kernelized Stein Discrepancy](https://mlsanity.com/paper/2304.14762/) (2023)
- [Learning Gaussian-Bernoulli RBMs using Difference of Convex Functions Optimization](https://mlsanity.com/paper/2102.06228/) (2021)
- [Energy-based survival modelling using harmoniums](https://mlsanity.com/paper/2110.01960/) (2021)
- [Neural Boltzmann Machines](https://mlsanity.com/paper/2305.08337/) (2023)
- [Quantum Boltzmann Machines for Sample-Efficient Reinforcement Learning](https://mlsanity.com/paper/2511.04856/) (2025)

## Abstract (arXiv)

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.