# Sparse Boltzmann Machines with Structure Learning as Applied to Text Analysis

arXiv: https://arxiv.org/abs/1609.05294 · HTML: https://mlsanity.com/paper/1609.05294/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Sep 2016.

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

- [Optimizing Connectivity through Network Gradients for Restricted Boltzmann Machines](https://mlsanity.com/paper/2209.06932/) (2022)

## Abstract (arXiv)

We are interested in exploring the possibility and benefits of structure learning for deep models. As the first step, this paper investigates the matter for Restricted Boltzmann Machines (RBMs). We conduct the study with Replicated Softmax, a variant of RBMs for unsupervised text analysis. We present a method for learning what we call Sparse Boltzmann Machines, where each hidden unit is connected to a subset of the visible units instead of all of them. Empirical results show that the method yields models with significantly improved model fit and interpretability as compared with RBMs where each hidden unit is connected to all visible units.