Globally Interpretable Classifiers via Boolean Formulas with Dynamic Propositions
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917683181649920 |
|---|---|
| author | Jaakkola, Reijo Janhunen, Tomi Kuusisto, Antti Rankooh, Masood Feyzbakhsh Vilander, Miikka |
| author_facet | Jaakkola, Reijo Janhunen, Tomi Kuusisto, Antti Rankooh, Masood Feyzbakhsh Vilander, Miikka |
| contents | Interpretability and explainability are among the most important challenges of modern artificial intelligence, being mentioned even in various legislative sources. In this article, we develop a method for extracting immediately human interpretable classifiers from tabular data. The classifiers are given in the form of short Boolean formulas built with propositions that can either be directly extracted from categorical attributes or dynamically computed from numeric ones. Our method is implemented using Answer Set Programming. We investigate seven datasets and compare our results to ones obtainable by state-of-the-art classifiers for tabular data, namely, XGBoost and random forests. Over all datasets, the accuracies obtainable by our method are similar to the reference methods. The advantage of our classifiers in all cases is that they are very short and immediately human intelligible as opposed to the black-box nature of the reference methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_01114 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Globally Interpretable Classifiers via Boolean Formulas with Dynamic Propositions Jaakkola, Reijo Janhunen, Tomi Kuusisto, Antti Rankooh, Masood Feyzbakhsh Vilander, Miikka Machine Learning Artificial Intelligence Logic in Computer Science I.2.6; F.4.1; I.2.4 Interpretability and explainability are among the most important challenges of modern artificial intelligence, being mentioned even in various legislative sources. In this article, we develop a method for extracting immediately human interpretable classifiers from tabular data. The classifiers are given in the form of short Boolean formulas built with propositions that can either be directly extracted from categorical attributes or dynamically computed from numeric ones. Our method is implemented using Answer Set Programming. We investigate seven datasets and compare our results to ones obtainable by state-of-the-art classifiers for tabular data, namely, XGBoost and random forests. Over all datasets, the accuracies obtainable by our method are similar to the reference methods. The advantage of our classifiers in all cases is that they are very short and immediately human intelligible as opposed to the black-box nature of the reference methods. |
| title | Globally Interpretable Classifiers via Boolean Formulas with Dynamic Propositions |
| topic | Machine Learning Artificial Intelligence Logic in Computer Science I.2.6; F.4.1; I.2.4 |
| url | https://arxiv.org/abs/2406.01114 |