EUVIMEDEUVIMED entdecken
Crossref

Explainable Bayesian Deep Learning through Input-skip Latent Binary Bayesian Neural Networks

Eirik Høyheim, Lars Skaaret-Lund, Solve Sæbø, Aliaksandr Hubin

Journal of Artificial Intelligence Research · 01.07.2026 · 86

DOI: 10.1613/jair.1.20433 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Artificial Intelligence Research, online erschienen am 01.07.2026. Verfasst von Eirik Høyheim und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Modeling natural phenomena with artificial neural networks (ANNs) often provides highly accurate predictions. However, ANNs often suffer from over-parameterization, complicating interpretation and raising uncertainty issues. Bayesian neural networks (BNNs) address the latter by representing weights as probability distributions, allowing for predictive uncertainty evaluation. Latent binary Bayesian neural networks (LBBNNs) further handle structural uncertainty and sparsify models by removing redundant weights. This article advances LBBNNs by enabling covariates to skip to any succeeding layer or be excluded, simplifying networks and clarifying input impacts on predictions. This further allows us to learn simpler structures (e.g., linear or even constant intercept only models) when appropriate. Furthermore, the input-skip LBBNN (ISLaB) approach reduces network density significantly compared to standard LBBNNs, achieving over 99% reduction for small networks and over 99.9% for larger ones, while still maintaining high predictive accuracy and uncertainty quantification. For example, on MNIST, we reached 97% accuracy and great calibration with just 935 weights, reaching state-of-the-art for compression of neural networks. Furthermore, the proposed method accurately identifies the true covariates and adjusts for system non-linearity. The main contribution is the introduction of active paths, enhancing directly designed global and local explanations within the LBBNN framework. The latter are exact with theoretical guarantees and do not require post hoc external tools.

Zitieren

APA

Høyheim, E., Skaaret-Lund, L., Sæbø, S., & Hubin, A. (2026). Explainable Bayesian Deep Learning through Input-skip Latent Binary Bayesian Neural Networks. Journal of Artificial Intelligence Research, 86. https://doi.org/10.1613/jair.1.20433

Vancouver

Høyheim E, Skaaret-Lund L, Sæbø S, Hubin A. Explainable Bayesian Deep Learning through Input-skip Latent Binary Bayesian Neural Networks. Journal of Artificial Intelligence Research. 2026;86. doi:10.1613/jair.1.20433

BibTeX
@article{Hyheim2026,
  author = {Høyheim, Eirik and Skaaret-Lund, Lars and Sæbø, Solve and Hubin, Aliaksandr},
  title = {Explainable Bayesian Deep Learning through Input-skip Latent Binary Bayesian Neural Networks},
  journal = {Journal of Artificial Intelligence Research},
  year = {2026},
  volume = {86},
  doi = {10.1613/jair.1.20433}
}
Kostenlos starten →