Bridging Symbolic and Sub-Symbolic AI: Towards Cooperative Transfer Learning in Multi-Agent Systems

Matteo Magnini, Giovanni Ciatto, Andrea Omicini

Cooperation and knowledge sharing are of paramount importance in the evolution of an intelligent species. Knowledge sharing requires a set of symbols with a shared interpretation, enabling effective communication supporting cooperation. The engineering of intelligent systems may then benefit from the distribution of knowledge among multiple components capable of cooperation and symbolic knowledge sharing. Accordingly, in this paper, we propose a roadmap for the exploitation of knowledge representation and sharing to foster higher degrees of artificial intelligence. We do so by envisioning intelligent systems as composed by multiple agents, capable of cooperative (transfer) learning—Co(T)L for short. In CoL, agents can improve their local (sub-symbolic) knowledge by exchanging (symbolic) information among each others. In CoTL, agents can also learn new tasks autonomously by sharing information about similar tasks. Along this line, we motivate the introduction of Co(T)L and discuss benefits and feasibility.

(keywords) transfer learning; multi-agent systems; artificial general intelligence; symbolic knowledge extraction; symbolic knowledge injection


  • 21th International Conference of the Italian Association for Artificial Intelligence (AIxIA 2022) — 28/11/2022–02/12/2022


Publications / Personal

Publications / Views

tags  |  authors  |  editors  |  journals
per year
2023  |  2022  |  2021  |  2020  |  2019  |  2018  |  2017  |  2016  |  2015  |  2014–1927
per sort
in journal  |  in proc  |  chapters  |  books  |  edited  |  spec issues  |  editorials  |  entries  |  manuals  |  tech reps  |  phd th  |  others
per status
online  |  in press  |  proof  |  camera-ready  |  revised  |  accepted  |  revision  |  submitted  |  draft  |  note
ACM Digital Library  |  DBLP  |  IEEE Xplore  |  IRIS  |  PubMed  |  Google Scholar  |  Scopus  |  Semantic Scholar  |  Web of Science  |  DOI

Partita IVA: 01131710376 — Copyright © 2008–2023 APICe@DISI – PRIVACY