- author = "Aidan Murphy and Grainne Murphy and Jorge Amaral and Douglas Mota Dias and Enrique Naredo and Conor Ryan",
- title = "Towards incorporating Human Knowledge in Fuzzy Pattern Tree Evolution",
- booktitle = "EuroGP 2021: Proceedings of the 24th European Conference on Genetic Programming",
- year = "2021",
- editor = "Ting Hu and Nuno Lourenco and Eric Medvet",
- series = "LNCS",
- volume = "12691",
- publisher = "Springer Verlag",
- address = "Virtual Event",
- pages = "66--81",
- month = "7-9 " # apr,
- organisation = "EvoStar, Species",
- note = "Best paper",
- keywords = "genetic algorithms, genetic programming, Grammatical Evolution, GE, Fuzzy logic, Explainable AI, XAI",
- isbn13 = "978-3-030-72811-3",
-
URL = "
http://www.human-competitive.org/sites/default/files/murphy_humies.txt",
-
URL = "
http://www.human-competitive.org/sites/default/files/eurogp21.pdf",
-
DOI = "
doi:10.1007/978-3-030-72812-0_5",
- size = "16 pages",
- abstract = "we show empirically that Fuzzy Pattern Trees (FPT) evolved using Grammatical Evolution (GE), a system we call FGE, meet the criteria to be considered a robust Explainable Artificial Intelligence (XAI) system. Experimental results show FGE achieves competitive results against state of the art black box methods on a set of real world benchmark problems. Various selection methods were investigated to see which was best for finding smaller, more interpretable models and a human expert was recruited to test the interpretability of the models found and to give a confidence score for each model. Models which were deemed interpretable but not trustworthy by the expert were seen to be outperformed in classification accuracy by interpretable models which were judge trustworthy, validating that FGE can be a powerful XAI technique.",
-
notes = "Entered 2021 HUMIES
common sense, how to trust AI, how to get new knowledge. Global explainable model, human (unambiguous) comprehensible. Linguistic (fuzzy) natural language, tree. Fuzzy pattern tree (functions and leafs all in the range 0..1). Multiple trees one per class (take max, winner takes all, WTA). UCI heart disease. GE grammar (Fuzzy-GE FGE). fitness = root mean error, Parsimony pressure, limit tree depth < 3. Sensible GE initialisation. GE results given to human expert (UCI heart data). 6 other problems. SVM, random forest, regression. GE intron removal.
http://www.evostar.org/2021/eurogp/ Part of \cite{Hu:2021:GP} EuroGP'2021 held in conjunction with EvoCOP2021, EvoMusArt2021 and EvoApplications2021",
