{"version":1,"type":"story","url":"https://digestai.news/story/researchers-introduce-neural-networks-with-differentiable-belief-funct","json":"https://digestai.news/story/researchers-introduce-neural-networks-with-differentiable-belief-funct.json","markdown":"https://digestai.news/story/researchers-introduce-neural-networks-with-differentiable-belief-funct.md","slug":"researchers-introduce-neural-networks-with-differentiable-belief-funct","headline":"Researchers introduce Neural networks with differentiable Belief-Function layers","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.\n\nIn 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.","keyPoints":["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"],"whyItMatters":"The work offers a principled way to encode uncertainty in deep nets, improving interpretability and out‑of‑distribution detection without costly calibration.","category":{"slug":"research","name":"Research","url":"https://digestai.news/category/research"},"entities":{"companies":[],"models":[],"people":["Yager","Dempster"]},"firstPublishedAt":"2026-10-23T04:00:00Z","updatedAt":"2026-10-23T04:00:00Z","sourceCount":1,"hasPrimarySource":true,"sources":[{"outlet":"arXiv cs.AI","title":"Neural Networks with Differentiable Belief-Function Layers","url":"https://arxiv.org/abs/2610.30173","publishedAt":"2026-10-23T04:00:00Z","type":"primary","primary":true,"lead":true}],"sourceNotes":null,"discussions":[],"thread":null,"cite":{"text":"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","publisher":"Digest AI","title":"Researchers introduce Neural networks with differentiable Belief-Function layers","datePublished":"2026-10-23T04:00:00Z","url":"https://digestai.news/story/researchers-introduce-neural-networks-with-differentiable-belief-funct"},"generatedBy":"Written by Digest AI's editorial model from the linked sources; the sources are the record.","license":"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"}