# Researchers introduce Neural networks with differentiable Belief-Function layers

Digest AI · Research · published 2026-10-23T04:00:00Z

Canonical: https://digestai.news/story/researchers-introduce-neural-networks-with-differentiable-belief-funct

## Summary

The authors present a deep evidential pipeline that replaces the standard Dempster–Shafer normaliser with Yager’s 1987 rule of combination. The new rule is bilinear and avoids the $(1-\kappa)^{-2}$ term that causes gradient divergence when evidence sources disagree.

In experiments on CIFAR‑10H, Yager’s vacuity is 9× larger on the most contested images, making the network’s ignorance output $m(\Theta)$ a readable "I do not know" signal. The model also performs competitively on out‑of‑distribution detection against strong single‑pass baselines, while a clamped Dempster variant becomes gradient‑unstable once the clamp is removed.

## Key points

- Authors use Yager's rule to avoid gradient divergence in belief‑function layers
- Yager's vacuity is 9× larger than Dempster's on contested CIFAR‑10H images
- The network's ignorance output serves as an "I do not know" signal

## Why it matters

The work offers a principled way to encode uncertainty in deep nets, improving interpretability and out‑of‑distribution detection without costly calibration.

## Sources

1. [Neural Networks with Differentiable Belief-Function Layers](https://arxiv.org/abs/2610.30173) (arXiv cs.AI, 2026-10-23, primary source)

## Cite

Digest AI, "Researchers introduce Neural networks with differentiable Belief-Function layers", 23 October 2026, https://digestai.news/story/researchers-introduce-neural-networks-with-differentiable-belief-funct

---

Written by Digest AI's editorial model from the linked sources; the sources are the record. Headlines, digests and key points are written by Digest AI and may be quoted with a link to the story page. Linked articles belong to their publishers. Terms: https://digestai.news/terms#reuse
JSON: https://digestai.news/story/researchers-introduce-neural-networks-with-differentiable-belief-funct.json