**arXiv ID:** 2403.06235 **Authors:** Pedro Zuidberg Dos Martires **Published:** 2024-03-10T15:25:49Z **Abstract:** Probabilistic circuits (PCs) have gained prominence in recent years as a versatile framework for discussing probabilistic models that support tractable queries and are yet expressive enough to model complex probability distributions. Nevertheless, tractability comes at a cost: PCs are less expressive than neural networks. In this paper we introduce probabilistic neural circuits ...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Probabilistic Neural Circuits?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-probabilistic-neural-circuits)
# Probabilistic Neural Circuits
**arXiv ID:** 2403.06235
**Authors:** Pedro Zuidberg Dos Martires
**Published:** 2024-03-10T15:25:49Z
**Abstract:**
Probabilistic circuits (PCs) have gained prominence in recent years as a versatile framework for discussing probabilistic models that support tractable queries and are yet expressive enough to model complex probability distributions. Nevertheless, tractability comes at a cost: PCs are less expressive than neural networks. In this paper we introduce probabilistic neural circuits (PNCs), which strike a balance between PCs and neural nets in terms of tractability and expressive power. Theoretically, we show that PNCs can be interpreted as deep mixtures of Bayesian networks. Experimentally, we demonstrate that PNCs constitute powerful function approximators.
## Skill Description
This skill is generated from the arXiv paper: Probabilistic Neural Circuits (2403.06235).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2403.06235](http://arxiv.org/abs/2403.06235v1)
