We propose a novel method to inject symbolic knowledge in form of Datalog formulae 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 formulae 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.
hosting event
reference publication
funding project
EXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge
(01/04/2021–31/03/2024)
works as
reference talk for