Switch to: References

Citations of:

Pink panthers and toothless tigers: three problems in classification

In Guendalina Righetti, Daniele Porello, Oliver Kutz, Nicolas Troquard & Claudio Masolo (eds.), Proceedings of the 7th International Workshop on Artificial Intelligence and Cognition, Manchester, UK, September 10-11, 2019. {CEUR} Workshop Proceedings 2483. pp. 39-53 (2019)

Add citations

You must login to add citations.
  1. Towards Knowledge-driven Distillation and Explanation of Black-box Models.Roberto Confalonieri, Guendalina Righetti, Pietro Galliani, Nicolas Toquard, Oliver Kutz & Daniele Porello - 2021 - In Roberto Confalonieri, Guendalina Righetti, Pietro Galliani, Nicolas Toquard, Oliver Kutz & Daniele Porello (eds.), Proceedings of the Workshop on Data meets Applied Ontologies in Explainable {AI} {(DAO-XAI} 2021) part of Bratislava Knowledge September {(BAKS} 2021), Bratislava, Slovakia, September 18th to 19th, 2021. CEUR 2998.
    We introduce and discuss a knowledge-driven distillation approach to explaining black-box models by means of two kinds of interpretable models. The first is perceptron (or threshold) connectives, which enrich knowledge representation languages such as Description Logics with linear operators that serve as a bridge between statistical learning and logical reasoning. The second is Trepan Reloaded, an ap- proach that builds post-hoc explanations of black-box classifiers in the form of decision trees enhanced by domain knowledge. Our aim is, firstly, to target (...)
    Download  
     
    Export citation  
     
    Bookmark  
  • Perceptron Connectives in Knowledge Representation.Pietro Galliani, Guendalina Righetti, Daniele Porello, Oliver Kutz & Nicolas Toquard - 2020 - In Pietro Galliani, Guendalina Righetti, Daniele Porello, Oliver Kutz & Nicolas Toquard (eds.), Knowledge Engineering and Knowledge Management - 22nd International Conference, {EKAW} 2020, Bolzano, Italy, September 16-20, 2020, Proceedings. Lecture Notes in Computer Science 12387. pp. 183-193.
    We discuss the role of perceptron (or threshold) connectives in the context of Description Logic, and in particular their possible use as a bridge between statistical learning of models from data and logical reasoning over knowledge bases. We prove that such connectives can be added to the language of most forms of Description Logic without increasing the complexity of the corresponding inference problem. We show, with a practical example over the Gene Ontology, how even simple instances of perceptron connectives are (...)
    Download  
     
    Export citation  
     
    Bookmark   2 citations  
  • Concept Combination in Weighted Logic.Guendalina Righetti, Claudio Masolo, Nicolas Toquard, Oliver Kutz & Daniele Porello - 2021 - In Guendalina Righetti, Claudio Masolo, Nicolas Toquard, Oliver Kutz & Daniele Porello (eds.), Proceedings of the Joint Ontology Workshops 2021 Episode {VII:} The Bolzano Summer of Knowledge co-located with the 12th International Conference on Formal Ontology in Information Systems {(FOIS} 2021), and the 12th Internati.
    We present an algorithm for concept combination inspired and informed by the research in cognitive and experimental psychology. Dealing with concept combination requires, from a symbolic AI perspective, to cope with competitive needs: the need for compositionality and the need to account for typicality effects. Building on our previous work on weighted logic, the proposed algorithm can be seen as a step towards the management of both these needs. More precisely, following a proposal of Hampton [1], it combines two weighted (...)
    Download  
     
    Export citation  
     
    Bookmark