KINS: Knowledge Injection via Network Structuring

   Info_icon.svg   dati    Eye_icon.svg   allegati    BibTeX_logo.svg   bibtex
Roberta Calegari, Giovanni Ciatto, Andrea Omicini (a cura di)
CILC 2022 – Italian Conference on Computational Logic, pp. 254–267
CEUR Workshop Proceedings (AI*IA Series) 3204
CEUR-WS
2022

We propose a novel method to inject symbolic knowledge in form of Datalog formulæ into neural networks (NN), called KINS (Knowledge Injection via Network Structuring). The idea behind our method is to extend NN internal structure with ad-hoc layers built out the injected symbolic knowledge. KINS does not constrain NN to any specific architecture, neither requires logic formulæ to be ground. Moreover, it is robust w.r.t. both lack of data and imperfect/incomplete knowledge. Experiments are reported to demonstrate the potential of KINS.

parole chiave   neural network, explainable AI, symbolic knowledge injection, KINS, PSyKI
presentazione di riferimento
Talk_icon.svg KINS: Knowledge Injection via Network Structuring (CILC 2022, 01/07/2022) — Matteo Magnini
evento origine
rivista o collana
Journal_icon.svg CEUR Workshop Proceedings (CEUR-WS.org)
pubblicazione contenitore
Publication_icon.svg CILC 2022 – Italian Conference on Computational Logic (curatela, 2022) — Roberta Calegari, Giovanni Ciatto, Andrea Omicini
progetto finanziatore
Project_icon.svg EXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)
funge da
pubblicazione di riferimento per presentazione
Talk_icon.svg KINS: Knowledge Injection via Network Structuring (CILC 2022, 01/07/2022) — Matteo Magnini