Symbolic Explanation Module for Fuzzy Cognitive Map-Based Reasoning Models
| Autor: | Gonzalo Nápoles, Fabian Hoitsma, Andreas Knoben, Maikel Leon Espinosa |
|---|---|
| Přispěvatelé: | Cognitive Science & AI |
| Rok vydání: | 2020 |
| Předmět: | |
| Zdroj: | Lecture Notes in Computer Science ISBN: 9783030637989 SGAI Conf. Tilburg University-PURE Artificial Intelligence XXXVII, 21-34 STARTPAGE=21;ENDPAGE=34;TITLE=Artificial Intelligence XXXVII |
| DOI: | 10.1007/978-3-030-63799-6_2 |
| Popis: | In recent years, pattern classification has started to move from computing models with outstanding prediction rates to models able to reach a suitable trade-off between accuracy and interpretability. Fuzzy Cognitive Maps (FCMs) and their extensions are recurrent neural networks that have been partially exploited towards fulfilling such a goal. However, the interpretability of these neural systems has been confined to the fact that both neural concepts and weights have a well-defined meaning for the problem being modeled. This rather naive assumption oversimplifies the complexity behind an FCM-based classifier. In this paper, we propose a symbolic explanation module that allows extracting useful insights and patterns from a trained FCM-based classifier. The proposed explanation module is implemented in Prolog and can be seen as a reverse symbolic reasoning rule that infers the inputs to be provided to the model to obtain the desired output. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|