Work

Deep belief networks are exact

Year: 2026
Type: preprint
Abstract: We prove that every strictly positive probability distribution on \(\{-1,1\}^n\) is represented exactly by a sigmoid belief network with finite parameters. This answers a question of Sutskever and Hinton. The proof upgrades their probability-sharing approximation to exact representation using Brouwer's fixed-point theorem.
Language: English
Open Access status: green
OpenAlex ID: W7212060292
Cites:
Cited by:
Related to: 10