Explainable AI Beer Style Classifier. Alonso, J., Ramos Soto, A., Castiello, C., & Mencar, C. In June, 2018.
abstract   bibtex   
This paper describes how to build an eXplainable Artificial Intelligence (XAI) classifier for a real use case related to beer style classification. It combines an opaque machine learning algorithm (Random Forest) with an interpretable machine learning algorithm (Decision Tree). The result is a XAI classifier which provides users with a good interpretability-accuracy trade-off but also with explanation capabilities. First, the opaque algorithm acts as an “oracle” which finds out the most plausible output. Then, we generate a textual explanation of the given output which emerges as an automatic interpretation of the inference process carried out by the related decision tree. We apply a Natural Language Generation Approach to generate the textual explanations.
@inproceedings{alonso_explainable_2018,
	title = {Explainable {AI} {Beer} {Style} {Classifier}},
	abstract = {This paper describes how to build an eXplainable Artificial Intelligence (XAI) classifier for a real use case related to beer style classification. It combines an opaque machine learning algorithm (Random Forest) with an interpretable machine learning algorithm (Decision Tree). The result is a XAI classifier which provides users with a good interpretability-accuracy trade-off but also with explanation capabilities. First, the opaque algorithm acts as an “oracle” which finds out the most plausible output. Then, we generate a textual explanation of the given output which emerges as an automatic interpretation of the inference process carried out by the related decision tree. We apply a Natural Language Generation Approach to generate the textual explanations.},
	author = {Alonso, Jose and Ramos Soto, Alejandro and Castiello, Ciro and Mencar, Corrado},
	month = jun,
	year = {2018},
}

Downloads: 0