A long-standing ambition in artificial intelligence is to integrate predictors’ inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from symbolic knowledge). Many methods in the literature support injection of symbolic knowledge into predictors, generally following the purpose of attaining better (i.e., more effective or efficient w.r.t. predictive performance) predictors. However, to the best of our knowledge, running implementations of these algorithms are currently either proof of concepts or unavailable in most cases. Moreover, a unified, coherent software framework supporting them as well as their interchange, comparison, and exploitation in arbitrary ML workflows is currently missing. Accordingly, in this paper we present the design of PSyKI, a platform providing general-purpose support to symbolic knowledge injection into predictors via different algorithms. In particular, we discuss the overall architecture, and the many components/functionalities of PSyKI, invidually—providing examples as well. We finally demonstrate the versatility of our approach by exemplifying two custom injection algorithms in a toy scenario: Poker Hands classification.

On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors / Matteo Magnini, Giovanni Ciatto, Andrea Omicini. - STAMPA. - 13283:(2022), pp. 90-108. (Intervento presentato al convegno 4th International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems (EXTRAAMAS 2022) tenutosi a Auckland, New Zealand nel 9–10 May 2022) [10.1007/978-3-031-15565-9_6].

On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors

Matteo Magnini;Giovanni Ciatto;Andrea Omicini
2022

Abstract

A long-standing ambition in artificial intelligence is to integrate predictors’ inductive features (i.e., learning from examples) with deductive capabilities (i.e., drawing inferences from symbolic knowledge). Many methods in the literature support injection of symbolic knowledge into predictors, generally following the purpose of attaining better (i.e., more effective or efficient w.r.t. predictive performance) predictors. However, to the best of our knowledge, running implementations of these algorithms are currently either proof of concepts or unavailable in most cases. Moreover, a unified, coherent software framework supporting them as well as their interchange, comparison, and exploitation in arbitrary ML workflows is currently missing. Accordingly, in this paper we present the design of PSyKI, a platform providing general-purpose support to symbolic knowledge injection into predictors via different algorithms. In particular, we discuss the overall architecture, and the many components/functionalities of PSyKI, invidually—providing examples as well. We finally demonstrate the versatility of our approach by exemplifying two custom injection algorithms in a toy scenario: Poker Hands classification.
2022
Explainable and Transparent AI and Multi-Agent Systems
90
108
On the Design of PSyKI: a Platform for Symbolic Knowledge Injection into Sub-Symbolic Predictors / Matteo Magnini, Giovanni Ciatto, Andrea Omicini. - STAMPA. - 13283:(2022), pp. 90-108. (Intervento presentato al convegno 4th International Workshop on Explainable, Transparent Autonomous Agents and Multi-Agent Systems (EXTRAAMAS 2022) tenutosi a Auckland, New Zealand nel 9–10 May 2022) [10.1007/978-3-031-15565-9_6].
Matteo Magnini, Giovanni Ciatto, Andrea Omicini
File in questo prodotto:
File Dimensione Formato  
ski-extraamas-2022.pdf

Open Access dal 23/09/2023

Tipo: Postprint
Licenza: Licenza per accesso libero gratuito
Dimensione 1.44 MB
Formato Adobe PDF
1.44 MB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11585/899511
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 5
  • ???jsp.display-item.citation.isi??? 2
social impact