{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T07:40:07Z","timestamp":1733125207126,"version":"3.30.0"},"reference-count":21,"publisher":"SAGE Publications","issue":"1","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IA"],"published-print":{"date-parts":[[2023,6,7]]},"abstract":"The XAI community is currently studying and developing symbolic knowledge-extraction (SKE) algorithms as a means to produce human-intelligible explanations for black-box machine learning predictors, so as to achieve believability in human-machine interaction. However, many extraction procedures exist in the literature, and choosing the most adequate one is increasingly cumbersome, as novel methods keep on emerging. Challenges arise from the fact that SKE algorithms are commonly defined based on theoretical assumptions that typically hinder practical applicability. This paper focuses on hypercube-based SKE methods, a quite general class of extraction techniques mostly devoted to regression-specific tasks. We first show that hypercube-based methods are flexible enough to support classification problems as well, then we propose a general model for them, and discuss how they support SKE on datasets, predictors, or learning tasks of any sort. Empirical examples are reported as well \u2013based upon the PSyKE framework \u2013, showing the applicability of hypercube-based methods to actual classification tasks.<\/jats:p>","DOI":"10.3233\/ia-230001","type":"journal-article","created":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T14:06:57Z","timestamp":1686319617000},"page":"63-75","source":"Crossref","is-referenced-by-count":3,"title":["Towards a unified model for symbolic knowledge extraction with hypercube-based methods"],"prefix":"10.1177","volume":"17","author":[{"given":"Federico","family":"Sabbatini","sequence":"first","affiliation":[{"name":"Dipartimento di Scienze Pure e Applicate (DiSPeA), Universit\u00e0 di Urbino, Urbino, Italy"}]},{"given":"Giovanni","family":"Ciatto","sequence":"additional","affiliation":[{"name":"Dipartimento di Informatica\u2013Scienza e Ingegneria (DISI), Universit\u00e0 di Bologna, Bologna, Italy"}]},{"given":"Roberta","family":"Calegari","sequence":"additional","affiliation":[{"name":"Dipartimento di Informatica\u2013Scienza e Ingegneria (DISI), Universit\u00e0 di Bologna, Bologna, Italy"}]},{"given":"Andrea","family":"Omicini","sequence":"additional","affiliation":[{"name":"Dipartimento di Informatica\u2013Scienza e Ingegneria (DISI), Universit\u00e0 di Bologna, Bologna, Italy"}]}],"member":"179","reference":[{"issue":"6","key":"10.3233\/IA-230001_ref1","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1016\/0950-7051(96)81920-4","article-title":"Survey and critique of techniques for extracting rules from trained artificial neural networks","volume":"8","author":"Andrews","year":"1995","journal-title":"Knowledge-Based Systems"},{"issue":"3","key":"10.3233\/IA-230001_ref3","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1287\/mnsc.49.3.312.12739","article-title":"Using neural network rule extraction and decision tables for credit-risk evaluation","volume":"49","author":"Baesens","year":"2003","journal-title":"Management Science"},{"issue":"5","key":"10.3233\/IA-230001_ref4","first-page":"1672","article-title":"Eclectic rule-extraction from support vector machines","volume":"2","author":"Barakat","year":"2008","journal-title":"International Journal of Computer and Information Engineering"},{"key":"10.3233\/IA-230001_ref5","first-page":"183","article-title":"Three medical examples in neural network rule extraction","volume":"13","author":"Bologna","year":"1997","journal-title":"Physica Medica"},{"key":"10.3233\/IA-230001_ref6","unstructured":"Breiman L. , Friedman J. , Stone C.J. and Olshen R.A. , Classification and Regression Trees. CRC Press, 1984."},{"issue":"1","key":"10.3233\/IA-230001_ref7","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3233\/IA-190036","article-title":"On the integration of symbolic and sub-symbolic techniques for XAI: A survey","volume":"14","author":"Calegari","year":"2020","journal-title":"Intelligenza Artificiale"},{"issue":"1","key":"10.3233\/IA-230001_ref14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2594473.2594475","article-title":"Comprehensible classification models: A position paper","volume":"15","author":"Freitas","year":"2014","journal-title":"ACM SIGKDD Explorations Newsletter"},{"issue":"1","key":"10.3233\/IA-230001_ref17","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.dss.2010.12.003","article-title":"An empirical evaluation of the comprehensibility of decision table, tree and rule based predictive models","volume":"51","author":"Huysmans","year":"2011","journal-title":"Decision Support Systems"},{"key":"10.3233\/IA-230001_ref18","doi-asserted-by":"crossref","first-page":"103459","DOI":"10.1016\/j.artint.2021.103459","article-title":"Explaining black-box classifiers using post-hoc explanations-by-example: The effect of explanations and error-rates in XAI user studies","volume":"294","author":"Kenny","year":"2021","journal-title":"Artificial Intelligence"},{"issue":"3","key":"10.3233\/IA-230001_ref20","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1145\/3236386.3241340","article-title":"The mythos of model interpretability","volume":"16","author":"Lipton","year":"2018","journal-title":"Queue"},{"issue":"3","key":"10.3233\/IA-230001_ref21","doi-asserted-by":"crossref","first-page":"1466","DOI":"10.1016\/j.ejor.2006.04.051","article-title":"Comprehensible credit scoring models using rule extraction from support vector machines","volume":"183","author":"Martens","year":"2007","journal-title":"European Journal of Operational Research"},{"issue":"3","key":"10.3233\/IA-230001_ref23","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1016\/S0020-7373(87)80053-6","article-title":"Simplifying decision trees","volume":"27","author":"Quinlan","year":"1987","journal-title":"International Journal of Man-Machine Studies"},{"key":"10.3233\/IA-230001_ref25","doi-asserted-by":"crossref","unstructured":"Rocha A. , Papa J.P. and Meira L.A.A. , How far do we get using machine learning black-boxes? International Journal of Pattern Recognition and Artificial Intelligence 26(02) (2012), 1261001\u2013(1\u201323).","DOI":"10.1142\/S0218001412610010"},{"issue":"1","key":"10.3233\/IA-230001_ref30","doi-asserted-by":"crossref","first-page":"27","DOI":"10.3233\/IA-210120","article-title":"Symbolic knowledge extraction from opaque ML predictors in PSyKE: Platform design & experiments","volume":"16","author":"Sabbatini","year":"2022","journal-title":"Intelligenza Artificiale"},{"issue":"3","key":"10.3233\/IA-230001_ref33","doi-asserted-by":"crossref","first-page":"90","DOI":"10.15406\/aaoaj.2022.06.00145","article-title":"Symbolic knowledge extraction from opaque predictors applied to cosmic-ray data gathered with LISA Pathfinder","volume":"6","author":"Sabbatini","year":"2022","journal-title":"Aeronautics and Aerospace Open Access Journal"},{"issue":"10","key":"10.3233\/IA-230001_ref34","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1016\/S0893-6080(02)00089-8","article-title":"Extracting regression rules from neural networks","volume":"15","author":"Saito","year":"2022","journal-title":"Neural Networks"},{"issue":"6","key":"10.3233\/IA-230001_ref35","doi-asserted-by":"crossref","first-page":"1392","DOI":"10.1109\/72.809084","article-title":"ANN-DT: An algorithm for extraction of decision trees from artificial neural networks","volume":"10","author":"Schmitz","year":"1999","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"04","key":"10.3233\/IA-230001_ref36","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1142\/S0129065711002821","article-title":"Rule extraction from minimal neural networks for credit card screening","volume":"21","author":"Setiono","year":"2011","journal-title":"International Journal of Neural Systems"},{"issue":"3","key":"10.3233\/IA-230001_ref37","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1109\/TNN.2002.1000125","article-title":"Extraction of rules from artificial neural networks for nonlinear regression","volume":"13","author":"Setiono","year":"2002","journal-title":"IEEE Transactions on Neural Networks"},{"issue":"5A","key":"10.3233\/IA-230001_ref38","first-page":"6","article-title":"Using neural network rule extraction for credit-risk evaluation","volume":"6","author":"Steiner","year":"2006","journal-title":"International Journal of Computer Science and Network Security"},{"issue":"1","key":"10.3233\/IA-230001_ref39","doi-asserted-by":"crossref","first-page":"71","DOI":"10.1007\/BF00993103","article-title":"Extracting refined rules from knowledge-based neural networks","volume":"13","author":"Towell","year":"1993","journal-title":"Machine Learning"}],"container-title":["Intelligenza Artificiale"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/IA-230001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T06:59:43Z","timestamp":1733122783000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/full\/10.3233\/IA-230001"}},"subtitle":[],"editor":[{"given":"Angelo","family":"Ferrando","sequence":"additional","affiliation":[]},{"given":"Viviana","family":"Mascardi","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,6,7]]},"references-count":21,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.3233\/ia-230001","relation":{},"ISSN":["1724-8035","2211-0097"],"issn-type":[{"type":"print","value":"1724-8035"},{"type":"electronic","value":"2211-0097"}],"subject":[],"published":{"date-parts":[[2023,6,7]]}}}