# Neural Boltzmann Machines

arXiv: https://arxiv.org/abs/2305.08337 · HTML: https://mlsanity.com/paper/2305.08337/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 20 references that are in the map.
- First posted on arXiv 15 May 2023.

## Builds on (most cited first, 11 of 11)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Deep Unsupervised Learning using Nonequilibrium Thermodynamics](https://mlsanity.com/paper/1503.03585/) (2015)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Training Compute-Optimal Large Language Models](https://mlsanity.com/paper/2203.15556/) (2022)
- [Deep Double Descent: Where Bigger Models and More Data Hurt](https://mlsanity.com/paper/1912.02292/) (2019)
- [Gaussian-Bernoulli RBMs Without Tears](https://mlsanity.com/paper/2210.10318/) (2022)
- [Deep learning for comprehensive forecasting of Alzheimer's Disease progression](https://mlsanity.com/paper/1807.03876/) (2018)
- [Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statistics](https://mlsanity.com/paper/1401.5900/) (2014)
- [Restricted Boltzmann Machine and Deep Belief Network: Tutorial and Survey](https://mlsanity.com/paper/2107.12521/) (2021)
- [Learning Gaussian-Bernoulli RBMs using Difference of Convex Functions Optimization](https://mlsanity.com/paper/2102.06228/) (2021)

## Built on by (most cited first, 1 of 1)

- [A Weighted Prognostic Covariate Adjustment Method for Efficient and Powerful Treatment Effect Inferences in Randomized Controlled Trials](https://mlsanity.com/paper/2309.14256/) (2023)

## Abstract (arXiv)

Conditional generative models are capable of using contextual information as input to create new imaginative outputs. Conditional Restricted Boltzmann Machines (CRBMs) are one class of conditional generative models that have proven to be especially adept at modeling noisy discrete or continuous data, but the lack of expressivity in CRBMs have limited their widespread adoption. Here we introduce Neural Boltzmann Machines (NBMs) which generalize CRBMs by converting each of the CRBM parameters to their own neural networks that are allowed to be functions of the conditional inputs. NBMs are highly flexible conditional generative models that can be trained via stochastic gradient descent to approximately maximize the log-likelihood of the data. We demonstrate the utility of NBMs especially with normally distributed data which has historically caused problems for Gaussian-Bernoulli CRBMs. Code to reproduce our results can be found at https://github.com/unlearnai/neural-boltzmann-machines.