Abstract
With the increasing prevalence of Machine Learning in everyday life, a growing number of people will be provided with Machine-Learned assessments on a regular basis. We believe that human users interacting with systems based on Machine-Learned classifiers will demand and profit from the systems’ decisions being explained in an approachable and comprehensive way. We developed a general process framework for logic-rule-based classifiers facilitating mutual exchange between system and user. The framework constitutes a guideline for how a system can apply Inductive Logic Programming in order to provide comprehensive explanations for classification choices and empowering users to evaluate and correct the system’s decisions. It also includes users’ corrections being integrated into the system’s core logic rules via retraining in order to increase the overall performance of the human-computer system. The framework suggests various forms of explanations—like natural language argumentations, near misses emphasizing unique characteristics, or image annotations—to be integrated into the system.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Bach S, Binder A, Montavon G, Klauschen F, Müller K-R, Samek W (2015) On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation. PLoS ONE 10(7):1–46
Ceri S, Gottlob G, Tanca L (1990) Logic programming and databases. Springer, Berlin
De Raedt L (2008) Logical and relational learning. Springer, Berlin
Džeroski S, Muggleton SH, Russell SJ (1992) Pac-learnability of determinate logic programs. In: COLT ’92: proceedings of the fifth annual workshop on computational learning theory, pp 128–135. https://doi.org/10.1145/130385.130399
Ekman P, Friesen WV (1978) The facial action coding system: a technique for the measurement of facial movement. Consulting Psychologists Press, Palo Alto
Escalante HJ, Escalera S, Guyon I, Baró X, Güçlütürk Y, Güçlü U, van Gerven M (eds) (2018) Explainable and interpretable models in computer vision and machine learning. Springer, Berlin
Kamilaris A, Kartakoullis A, Prenafeta-Boldú FX (2017) A review on the practice of big data analysis in agriculture. Comput Electron Agric 143:23–37
Lin D, Dechter E, Ellis K, Tenenbaum JB, Muggleton SH (2014) Bias reformulation for one-shot function induction. In: ECAI 2014, pp 525–530
Lombrozo T, Vasilyeva N (2017) Causal explanation. In: Waldmann M (ed) Oxford handbook of causal reasoning. Oxford University Press, Oxford, pp 415–432
Losing V, Hammer B, Wersing H (2018) Incremental on-line learning: a review and comparison of state of the art algorithms. Neurocomputing 275:1261–1274
Markman AB, Gentner D (1996) Commonalities and differences in similarity comparisons. Mem Cogn 24(2):235–249
Miller T (2019) Explanation in artificial intelligence: insights from the social sciences. Artif Intell 267:1–38
Muggleton S (1995) Inverse entailment and progol. New Gener Comput 13(3–4):245–286
Muggleton SH, De Raedt L (1994) Inductive logic programming: theory and methods. J Log Program 19–20:629–679
Muggleton SH, Lin D, Tamaddoni-Nezhad A (2015) Meta-interpretive learning of higher-order dyadic datalog: predicate invention revisited. Mach Learn 100:49–73
Muggleton SH, Schmid U, Zeller C, Tamaddoni-Nezhad A, Besold T (2018) Ultra-strong machine learning: comprehensibility of programs learned with ILP. Mach Learn 107(7):1119–1140. https://doi.org/10.1007/s10994-018-5707-3
Ribeiro MT, Singh S, Guestrin C (2016) “Why should I trust you?”: explaining the predictions of any classifier. SIGKDD 2016:1135–1144
Rieger I, Finzel B, Seuß D, Wittenberg T, Schmid U (2019) Make pain estimation transparent: a roadmap to fuse bayesian deep learning and inductive logic programming. In: IEEE EMBS 2019
Riguzzi F (2018) Foundations of probabilistic logic programming. River Publishers, Gistrup
Schmid U (2019) Cooperative learning with mutual explanations, 2019. In: Invited talk at human-like computing third wave of AI workshop, London, UK
Siebers M, Schmid U (2019) Please delete that! Why should I? Explaining learned irrelevance classifications of digital objects. KI - Künstliche Intelligenz 33(1):35–44. https://doi.org/10.1007/s13218-018-0565-5
Siebers M, Göbel K, Niessen C, Schmid U (2017a) Requirements for a companion system to support identifying irrelevancy. In: 2017 international conference on companion technology, pp 1–2. https://doi.org/10.1109/COMPANION.2017.8287076
Siebers M, Schmid U, Göbel K, Niessen C (2017b) A psychonic approach to the design of a cognitive companion supporting intentional forgetting. Kognitive Systeme. https://doi.org/10.17185/duepublico/44537
Srinivasan A (2004) The aleph manual. http://www.cs.ox.ac.uk/activities/machinelearning/Aleph/
Tintarev N, Masthoff J (2015) Explaining recommendations: design and evaluation. In: Ricci F, Rokach L, Shapira B (eds) Recommender systems handbook. Springer, Berlin, pp 353–382
Walicki M (2017) Introduction to mathematical logic. World Scientific, Singapore
Winston PH (1975) Learning structural descriptions from examples. In: Winston PH (ed) The psychology of computer vision. McGraw-Hill, New York, pp 157–210
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation)—318286042 (Dare2Del); 405630557 (PainFaceReader).
Rights and permissions
About this article
Cite this article
Gromowski, M., Siebers, M. & Schmid, U. A process framework for inducing and explaining Datalog theories. Adv Data Anal Classif 14, 821–835 (2020). https://doi.org/10.1007/s11634-020-00422-7
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11634-020-00422-7