- author = "Hormoz Shahrzad and Babak Hodjat and Risto Miikkulainen",
- title = "{EVOTER}: Evolution of Transparent Explainable Rule sets",
- journal = "ACM Transactions on Evolutionary Learning and Optimization",
- note = "Just Accepted",
- keywords = "genetic algorithms, genetic programming, Grammatical Evolution, rule set Evolution, Explainable AI, XAI, interpretable rule sets, AIC, BIC, BNF, Combine-rules crossover",
- ISSN = "2688-299X",
- publisher = "Association for Computing Machinery",
-
URL = "
http://www.cs.utexas.edu/users/ai-lab?shahrzad:telo24",
-
URL = "https://arxiv.org/abs/2204.10438",
-
URL = "https://doi.org/10.1145/3702651",
-
DOI = "
doi:10.1145/3702651",
- size = "32 pages",
- abstract = "Most AI systems are black boxes generating reasonable outputs for given inputs. Some domains, however, have explainability and trustworthiness requirements that cannot be directly met by these approaches. Various methods have therefore been developed to interpret black-box models after training. This paper advocates an alternative approach where the models are transparent and explainable to begin with. This approach, EVOTER, evolves rule sets based on extended propositional logic expressions. The approach is evaluated in several prediction/classification and prescription/policy search domains with and without a surrogate. It is shown to discover meaningful rule sets that perform similarly to black-box models. The rules can provide insight into the domain and make hidden biases explicit. It may also be possible to edit the rules directly to remove biases and add constraints. EVOTER thus forms a promising foundation for building trustworthy AI systems for real-world applications in the future.",
-
notes = "shahrzad2024evoterevolutiontransparentexplainable 25
Oct 2024 v5
UCI datasets: Iris, Breast Cancer, Human Activity Recognition, Credit Approval, Contraceptive Method Choice, Flappy Bird, Cart-Pole, Surrogate, 10 year USA Diabetes dataset,
https://dlnext.acm.org/journal/telo",
