Neuro-LENS: A Neuro-Symbolic Framework Integrating Incomplete Background Knowledge and Deep Learning
Neurosymbolic Artificial Intelligence · 2026-07 · 2
DOI: 10.1177/29498732261469489 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neurosymbolic Artificial Intelligence, online erschienen am 24.07.2026. Verfasst von Giulia Murtas und 2 weiteren Autor:innen. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
In this study, we propose Neuro-LENS, a neuro-symbolic evidence-based logic and symbolic reasoning framework that combines incomplete symbolic knowledge with neural learning to address ambiguity and improve the accuracy and interpretability of the results. We explore three strategies for integrating symbolic reasoning with deep learning and evaluate their effectiveness in practical settings: (i) applying the symbolic component to the neural output (neural-to-symbolic chaining); (ii) generating additional neural input features through symbolic rules (symbolic-to-neural chaining); (iii) creating an ensemble reasoning model (parallel neural-symbolic integration). The potential of the proposed Neuro-LENS framework is demonstrated on two real-world use cases: scene classification with abandoned object detection and prognostic health monitoring in vehicle failure prediction.
Zitieren
APA
Murtas, G., Boeva, V., & Tsiporkova, E. (2026). Neuro-LENS: A Neuro-Symbolic Framework Integrating Incomplete Background Knowledge and Deep Learning. Neurosymbolic Artificial Intelligence, 2. https://doi.org/10.1177/29498732261469489
Vancouver
Murtas G, Boeva V, Tsiporkova E. Neuro-LENS: A Neuro-Symbolic Framework Integrating Incomplete Background Knowledge and Deep Learning. Neurosymbolic Artificial Intelligence. 2026;2. doi:10.1177/29498732261469489
BibTeX
@article{Murtas2026,
author = {Murtas, Giulia and Boeva, Veselka and Tsiporkova, Elena},
title = {Neuro-LENS: A Neuro-Symbolic Framework Integrating Incomplete Background Knowledge and Deep Learning},
journal = {Neurosymbolic Artificial Intelligence},
year = {2026},
volume = {2},
doi = {10.1177/29498732261469489}
}
EUVIMED