Symbolic knowledge-extraction (SKE) techniques are currently employed for various purposes, particularly addressing the challenge of explaining opaque models by generating human-understandable explanations. The existing literature encompasses a diverse range of techniques, each relying on specific theoretical assumptions and possessing its own advantages and disadvantages. Amongst the available choices, hypercube-based SKE techniques are notable for their adaptability and versatility. However, they may suffer from limited completeness when utilised for making predictions. This research aims to augment the predictive capabilities of hypercube-based SKE techniques, striving for a completeness rate of 100%. Furthermore, the study includes experiments that assess the effectiveness of the proposed enhancements.
Achieving Complete Coverage with Hypercube-Based Symbolic Knowledge-Extraction Techniques / Sabbatini F.; Calegari R.. - ELETTRONICO. - 1947:(2023), pp. 179-197. (Intervento presentato al convegno International Workshops of the 26th European Conference on Artificial Intelligence, ECAI 2023 tenutosi a Krakow, Poland nel 2023) [10.1007/978-3-031-50396-2_10].
Achieving Complete Coverage with Hypercube-Based Symbolic Knowledge-Extraction Techniques
Calegari R.
2023
Abstract
Symbolic knowledge-extraction (SKE) techniques are currently employed for various purposes, particularly addressing the challenge of explaining opaque models by generating human-understandable explanations. The existing literature encompasses a diverse range of techniques, each relying on specific theoretical assumptions and possessing its own advantages and disadvantages. Amongst the available choices, hypercube-based SKE techniques are notable for their adaptability and versatility. However, they may suffer from limited completeness when utilised for making predictions. This research aims to augment the predictive capabilities of hypercube-based SKE techniques, striving for a completeness rate of 100%. Furthermore, the study includes experiments that assess the effectiveness of the proposed enhancements.File | Dimensione | Formato | |
---|---|---|---|
ximl-2023-vicinity.pdf
embargo fino al 21/01/2025
Tipo:
Postprint
Licenza:
Licenza per accesso libero gratuito
Dimensione
2.74 MB
Formato
Adobe PDF
|
2.74 MB | Adobe PDF | Visualizza/Apri Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.