Título | Prometheus: Harnessing Fuzzy Logic and Natural Language for Human-centric Explainable Artificial Intelligence |
---|---|
Autores | Ettore Mariotti‚ Jose M. Alonso-Moral‚ Albert Gatt |
Tipo | Comunicación para congreso |
Fonte | XX Spanish Congress on Fuzzy Logic and Technologies, Málaga‚ España, 2021. |
Abstract | Prometheus is an interpretable model which is suitable for the generation of visual and textual explanations grounded in common sense knowledge. This model can be seen as a special case of generalized additive models‚ which can be also interpreted as a list of (fuzzy) rules. The goodness of the model is illustrated with one benchmark dataset from the medical domain. Reported results are encouraging. They suggest that Prometheus exhibits a good balance between understandability and classification performance in comparison with other well-known models (e.g.‚ linear models‚ decision trees or fuzzy rule-based classifiers) which are deemed as interpretable. |
Palabras chave | XAI‚ Interpretable ML‚ Shapley Values‚ Generalized Additive Models‚ Fuzzy Logic |