---
format: "aidr-story-markdown/v1"
id: "fb9c71a9050ae7b2f21479088929e5448727100e8f651419dc11105db450d1c7"
canonical_url: "https://aidr.today/fb9c71a9?lang=en"
title: "Neural Networks with Differentiable Belief-Function Layers"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-23T04:00:00.000Z"
category: "Research"
topics: ["inference"]
source_urls: ["https://arxiv.org/abs/2610.30173"]
summary: "A new deep evidential pipeline incorporates differentiable belief-function layers using Yager's 1987 rule of combination, avoiding gradient divergence issues found in Dempster's normaliser. The network treats every mass in the chain as a valid Dempster–Shafer mass function and uses the output mass on the ignorance set as an uncertainty signal, ordering human disagreement in visual and linguistic modalities."
---

# Neural Networks with Differentiable Belief\-Function Layers

> [Open the canonical story](<https://aidr.today/fb9c71a9?lang=en>)

**Published:** 2026-10-23T04:00:00.000Z
**Category:** Research
**Topics:** inference

## Summary

A new deep evidential pipeline incorporates differentiable belief\-function layers using Yager's 1987 rule of combination, avoiding gradient divergence issues found in Dempster's normaliser\. The network treats every mass in the chain as a valid Dempster–Shafer mass function and uses the output mass on the ignorance set as an uncertainty signal, ordering human disagreement in visual and linguistic modalities\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.30173>)