---
title: "What kind of graphical model is the brain?"
authors:
  - "Geoffrey E. Hinton"
doi: ""
url: "https://ijcai.org/proceedings/2005/238"
pdf: "https://ijcai.org/proceedings/2005/0238.pdf"
venue: "Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence"
year: 2005
pages: "1765--1"
track: ""
keywords:
---

# What kind of graphical model is the brain?

Geoffrey E. Hinton

*Proceedings of the Nineteenth International Joint Conference on Artificial Intelligence*, pages 1765--1.

## Abstract

If neurons are treated as latent variables, our visual systems are non-linear, densely-connected graphical models containing billions of variables and thousands of billions of parameters. Current algorithms would have difficulty learning a graphical model of this scale. Starting with an algorithm that has difficulty learning more than a few thousand parameters, I describe a series of progressively better learning algorithms all of which are designed to run on neuron-like hardware. The latest member of this series can learn deep, multi-layer belief nets quite rapidly. It turns a generic network with three hidden layers and 1.7 million connections into a very good generative model of handwritten digits. After learning, the model gives classification performance that is comparable to the best discriminative methods.