Author:
Alòs Josep,Ansótegui Carlos,Torres Eduard
Abstract
AbstractWe present an approach to improve the accuracy-interpretability trade-off of Machine Learning (ML) Decision Trees (DTs). In particular, we apply Maximum Satisfiability technology to compute Minimum Pure DTs (MPDTs). We improve the runtime of previous approaches and, show that these MPDTs can outperform the accuracy of DTs generated with the ML framework sklearn.
Publisher
Springer Science and Business Media LLC
Subject
Artificial Intelligence,Linguistics and Language,Language and Linguistics
Reference32 articles.
1. Aglin G, Nijssen S, Schaus P (2020) Learning optimal decision trees using caching branch-and-bound search. In: AAAI 2020, IAAI 2020, EAAI 2020, New York, NY, USA, February 7–12, 2020. AAAI Press, pp 3146–3153, https://aaai.org/ojs/index.php/AAAI/article/view/5711
2. Ansótegui C, Ojeda J, Pacheco A et al (2021) Optilog: a framework for sat-based systems. In: SAT 2021, Cham, pp 1–10
3. Ansótegui C, Izquierdo I, Manyà F et al (2013) A max-sat-based approach to constructing optimal covering arrays. Front Artif Intell Appl 256:51–59
4. Avellaneda F (2020) Efficient inference of optimal decision trees. In: AAAI 2020, IAAI 2020, EAAI 2020, New York, NY, USA, February 7–12, 2020. AAAI Press, pp 3195–3202
5. Bacchus F, Berg J, Järvisalo M, et al (2021) Maxsat evaluation 2021: solver and benchmark descriptions
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献