2026· KR Doctoral Consortium· pp. 22-28· 0 citations· 15 references
Computer Science
TL;DR
A novel neuro-symbolic research path is presented that bridges sub-symbolic Machine Learning classifiers with symbolic techniques from the Knowledge Representation and Reasoning field and enables reasoning simultaneously on both the raw data features used by the classifiers and a symbolic intensional knowledge specified for the domain.
This paper provides its computational complexity analysis for ontologies specified in (the Description Logic counterpart of) RDFS, and binary Multi-Layer Perceptrons, and binary Multi-Layer Perceptrons.
Gianluca Cima, Marco Console, Laura Papi· Digital library· 0 citations
A neuro-symbolic framework for automatic CA that significantly reduces user involvement by introducing neural Oracle Transformer models which learn to emulate user responses and to generalize conceptual knowledge is proposed.
Nassim Belmecheri, Arnaud Gotlieb, Nadjib Lazaar et al.· 0 citations
A novel method called DKA is presented, which introduces a limited set of concept-supervised data to enhance the knowledge base, effectively solving the reasoning shortcut problem and improving the applicability of the NeSy system.
Yu-Feng Li, Xiao-Wen Yang, Wenda Wei et al.· Proceedings of the 32nd ACM...· 0 citations
UNICON is introduced, a foundation model that exhibits numerical intelligence across disciplines, and training-corpus diversity improves generalization to unseen disciplines and establishes UNICON as a foundation model of numerical intelligence.
Cheng-Ying Wu, Zong-Min Yu, Liu Yang· arXiv.org· 0 citations
This work develops a Description Logic–based general formalization of the structure underlying several types of bias, with explicit attention to the epistemic states of agents, to integrate ontological constraints with representations of agents’ epistemic attitudes, thereby connecting DL-based knowledge representation...
Mattia Petrolo, E. Kubyshkina· Digital library· 0 citations
Modern chemistry is pushing the limits of traditional Artificial Intelligence (AI) models, placing unprecedented demands on data availability to address humanity's most pressing challenges. One particular concern is AI's dependence on large, curated data and its tendency to deviate from or misrepresent fundamental...
José Ferraz-Caetano, Filipe Teixeira, M. N. D. S. Cordeiro· WIREs Computational Molecula...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
