{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T06:10:05Z","timestamp":1782972605154,"version":"3.54.5"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T00:00:00Z","timestamp":1710979200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T00:00:00Z","timestamp":1710979200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"\u201cUniversity SAL Labs\u201d initiative of Silicon Austria Labs (SAL) and its Austrian partner universities"},{"DOI":"10.13039\/501100011688","name":"Electronic Components and Systems for European Leadership","doi-asserted-by":"publisher","award":["101007350"],"award-info":[{"award-number":["101007350"]}],"id":[{"id":"10.13039\/501100011688","id-type":"DOI","asserted-by":"publisher"}]},{"name":"TU Graz LEAD project Dependable Internet of Things in Adverse Environments"},{"DOI":"10.13039\/501100005366","name":"Universitetet i Oslo","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100005366","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004955","name":"\u00d6sterreichische F\u00f6rschungsforderungsgesellschaft","doi-asserted-by":"publisher","award":["880852"],"award-info":[{"award-number":["880852"]}],"id":[{"id":"10.13039\/501100004955","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017488","name":"Utdannings- og forskningsdepartementet","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100017488","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Softw Syst Model"],"published-print":{"date-parts":[[2024,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this article, we present a novel approach to learning finite automata with the help of recurrent neural networks. Our goal is not only to train a neural network that predicts the observable behavior of an automaton but also to learn its structure, including the set of states and transitions. In contrast to previous work, we constrain the training with a specific regularization term. We iteratively adapt the architecture to learn the minimal automaton, in the case where the number of states is unknown. We evaluate our approach with standard examples from the automata learning literature, but also include a case study of learning the finite-state models of real Bluetooth Low Energy protocol implementations. The results show that we can find an appropriate architecture to learn the correct minimal automata in all considered cases.<\/jats:p>","DOI":"10.1007\/s10270-024-01160-6","type":"journal-article","created":{"date-parts":[[2024,3,21]],"date-time":"2024-03-21T05:01:56Z","timestamp":1710997316000},"page":"625-655","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Learning minimal automata with recurrent neural networks"],"prefix":"10.1007","volume":"23","author":[{"given":"Bernhard K.","family":"Aichernig","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandra","family":"K\u00f6nig","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cristinel","family":"Mateis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9446-9541","authenticated-orcid":false,"given":"Andrea","family":"Pferscher","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Tappler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,21]]},"reference":[{"key":"1160_CR1","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/978-3-319-96562-8_5","volume-title":"Machine Learning for Dynamic Software Analysis: Potentials and Limits","author":"F Howar","year":"2018","unstructured":"Howar, F., Steffen, B.: Active automata learning in practice. In: Bennaceur, A., H\u00e4hnle, R., Meinke, K. (eds.) Machine Learning for Dynamic Software Analysis: Potentials and Limits, pp. 123\u2013148. Springer, Cham (2018)"},{"key":"1160_CR2","doi-asserted-by":"crossref","unstructured":"Aichernig, B.K., Mostowski, W., Mousavi, M.R., Tappler, M., Taromirad, M.: Model learning and model-based testing. In: Machine Learning for Dynamic Software Analysis: Potentials and Limits\u2014International Dagstuhl Seminar 16172, pp. 74\u2013100. Springer, Cham (2018)","DOI":"10.1007\/978-3-319-96562-8_3"},{"key":"1160_CR3","doi-asserted-by":"crossref","unstructured":"Irfan, M.N., Oriat, C., Groz, R.: Model inference and testing. In: Advances in Computers, vol. 89, pp. 89\u2013139. Elsevier (2013)","DOI":"10.1016\/B978-0-12-408094-2.00003-5"},{"key":"1160_CR4","doi-asserted-by":"publisher","unstructured":"Oncina, J., Garcia, P.: Identifying regular languages in polynomial time. In: Advances in Structural and Syntactic Pattern Recognition. Machine Perception and Artificial Intelligence, vol. 5, pp. 99\u2013108. World Scientific (1992). https:\/\/doi.org\/10.1142\/9789812797919_0007","DOI":"10.1142\/9789812797919_0007"},{"issue":"2","key":"1160_CR5","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/0890-5401(87)90052-6","volume":"75","author":"D Angluin","year":"1987","unstructured":"Angluin, D.: Learning regular sets from queries and counterexamples. Inf. Comput. 75(2), 87\u2013106 (1987). https:\/\/doi.org\/10.1016\/0890-5401(87)90052-6","journal-title":"Inf. Comput."},{"issue":"3","key":"1160_CR6","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1007\/s11334-022-00449-3","volume":"18","author":"E Muskardin","year":"2022","unstructured":"Muskardin, E., Aichernig, B.K., Pill, I., Pferscher, A., Tappler, M.: AALpy: an active automata learning library. Innov. Syst. Softw. Eng. 18(3), 417\u2013426 (2022). https:\/\/doi.org\/10.1007\/s11334-022-00449-3","journal-title":"Innov. Syst. Softw. Eng."},{"key":"1160_CR7","doi-asserted-by":"crossref","unstructured":"Isberner, M., Howar, F., Steffen, B.: The open-source LearnLib\u2014a framework for active automata learning. In: CAV 2015. Part I, pp. 487\u2013495. Springer, Cham (2015)","DOI":"10.1007\/978-3-319-21690-4_32"},{"key":"1160_CR8","doi-asserted-by":"publisher","unstructured":"Grinchtein, O., Leucker, M., Piterman, N.: Inferring network invariants automatically. In: Furbach, U., Shankar, N. (eds.) Automated Reasoning, Third International Joint Conference, IJCAR 2006, Seattle, WA, USA, August 17\u201320, 2006, Proceedings. Lecture Notes in Computer Science, vol. 4130, pp. 483\u2013497. Springer, Berlin (2006). https:\/\/doi.org\/10.1007\/11814771_40","DOI":"10.1007\/11814771_40"},{"issue":"4","key":"1160_CR9","doi-asserted-by":"publisher","first-page":"825","DOI":"10.1007\/s10664-012-9222-z","volume":"18","author":"M Heule","year":"2013","unstructured":"Heule, M., Verwer, S.: Software model synthesis using satisfiability solvers. Empir. Softw. Eng. 18(4), 825\u2013856 (2013)","journal-title":"Empir. Softw. Eng."},{"key":"1160_CR10","doi-asserted-by":"publisher","unstructured":"Avellaneda, F., Petrenko, A.: FSM inference from long traces. In: Havelund, K., Peleska, J., Roscoe, B., de Vink, E.P. (eds.) Formal Methods\u201422nd International Symposium, FM 2018, Held as Part of the Federated Logic Conference, FloC 2018, Oxford, UK, July 15\u201317, 2018, Proceedings. Lecture Notes in Computer Science, vol. 10951, pp. 93\u2013109. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-95582-7_6","DOI":"10.1007\/978-3-319-95582-7_6"},{"key":"1160_CR11","doi-asserted-by":"crossref","unstructured":"Wallner, F., Aichernig, B.K., Burghard, C.: It\u2019s not a feature, it\u2019s a bug: fault-tolerant model mining from noisy data. In: 2024 IEEE\/ACM 46th International Conference on Software Engineering (ICSE), pp. 316\u2013328. IEEE Computer Society, Los Alamitos, CA, USA (2024). https:\/\/doi.ieeecomputersociety.org\/","DOI":"10.1145\/3597503.3623346"},{"key":"1160_CR12","doi-asserted-by":"crossref","unstructured":"Smetsers, R., Fiterau-Brostean, P., Vaandrager, F.W.: Model learning as a satisfiability modulo theories problem. In: LATA 2018. Ramat Gan, Israel, April 9\u201311, 2018, Proceedings, pp. 182\u2013194. Springer, Cham (2018)","DOI":"10.1007\/978-3-319-77313-1_14"},{"key":"1160_CR13","doi-asserted-by":"crossref","unstructured":"Tappler, M., Aichernig, B.K., Lorber, F.: Timed automata learning via SMT solving. In: NFM 2022. Pasadena, CA, USA, May 24\u201327, 2022, Proceedings, pp. 489\u2013507. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-06773-0_26"},{"issue":"3","key":"1160_CR14","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/S0019-9958(78)90562-4","volume":"37","author":"EM Gold","year":"1978","unstructured":"Gold, E.M.: Complexity of automaton identification from given data. Inf. Control 37(3), 302\u2013320 (1978). https:\/\/doi.org\/10.1016\/S0019-9958(78)90562-4","journal-title":"Inf. Control"},{"key":"1160_CR15","doi-asserted-by":"publisher","unstructured":"Aichernig, B.K., K\u00f6nig, S., Mateis, C., Pferscher, A., Schmidt, D., Tappler, M.: Constrained training of recurrent neural networks for automata learning. In: Schlingloff, B., Chai, M. (eds.) Software Engineering and Formal Methods\u201420th International Conference, SEFM 2022, Berlin, Germany, September 26\u201330, 2022, Proceedings. Lecture Notes in Computer Science, vol. 13550, pp. 155\u2013172. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-17108-6_10","DOI":"10.1007\/978-3-031-17108-6_10"},{"issue":"2","key":"1160_CR16","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1207\/s15516709cog1402_1","volume":"14","author":"JL Elman","year":"1990","unstructured":"Elman, J.L.: Finding structure in time. Cognit. Sci. 14(2), 179\u2013211 (1990). https:\/\/doi.org\/10.1207\/s15516709cog1402_1","journal-title":"Cognit. Sci."},{"issue":"6","key":"1160_CR17","doi-asserted-by":"publisher","first-page":"1780","DOI":"10.1109\/TNNLS.2019.2926466","volume":"31","author":"Y Ma","year":"2020","unstructured":"Ma, Y., Principe, J.C.: A taxonomy for neural memory networks. IEEE Trans. Neural Netw. Learn. Syst. 31(6), 1780\u20131793 (2020). https:\/\/doi.org\/10.1109\/TNNLS.2019.2926466","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1160_CR18","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139194655","volume-title":"Grammatical Inference: Learning Automata and Grammars","author":"C de la Higuera","year":"2010","unstructured":"de la Higuera, C.: Grammatical Inference: Learning Automata and Grammars. Cambridge University Press, New York (2010)"},{"key":"1160_CR19","doi-asserted-by":"publisher","unstructured":"Mao, H., Chen, Y., Jaeger, M., Nielsen, T.D., Larsen, K.G., Nielsen, B.: Learning Markov decision processes for model checking. In: Fahrenberg, U., Legay, A., Thrane, C.R. (eds.) Proceedings Quantities in Formal Methods, QFM 2012, Paris, France, 28 August 2012. EPTCS, vol. 103, pp. 49\u201363 (2012). https:\/\/doi.org\/10.4204\/EPTCS.103.6","DOI":"10.4204\/EPTCS.103.6"},{"key":"1160_CR20","unstructured":"Hopcroft, J.E., Motwani, R., Ullman, J.D.: Introduction to automata theory, languages, and computation. In: Pearson International Edition, 3rd edn. Addison-Wesley, USA (2007)"},{"key":"1160_CR21","doi-asserted-by":"publisher","unstructured":"Hopcroft, J.: An n log n algorithm for minimizing states in a finite automaton. In: Kohavi, Z., Paz, A. (eds.) Theory of Machines and Computations, pp. 189\u2013196. Academic Press, (1971). https:\/\/doi.org\/10.1016\/B978-0-12-417750-5.50022-1","DOI":"10.1016\/B978-0-12-417750-5.50022-1"},{"key":"1160_CR22","doi-asserted-by":"publisher","unstructured":"Shahbaz, M., Groz, R.: Inferring Mealy machines. In: FM. LNCS, vol. 5850, pp. 207\u2013222. Springer, Berlin (2009). https:\/\/doi.org\/10.1007\/978-3-642-05089-3_14","DOI":"10.1007\/978-3-642-05089-3_14"},{"key":"1160_CR23","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., Chintala, S.: PyTorch: an imperative style, high-performance deep learning library. In: NeurIPS, pp. 8024\u20138035. Curran Associates Inc. (2019)"},{"key":"1160_CR24","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)"},{"key":"1160_CR25","doi-asserted-by":"crossref","unstructured":"Tomita, M.: Dynamic construction of finite automata from examples using hill-climbing. In: Conference of the Cognitive Science Society, pp. 105\u2013108 (1982)","DOI":"10.21236\/ADA120123"},{"key":"1160_CR26","unstructured":"Weiss, G., Goldberg, Y., Yahav, E.: Extracting automata from recurrent neural networks using queries and counterexamples. In: ICML. Proceedings of Machine Learning Research, vol. 80, pp. 5244\u20135253. PMLR (2018)"},{"key":"1160_CR27","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.neucom.2021.04.058","volume":"452","author":"C Oliva","year":"2021","unstructured":"Oliva, C., Lago-Fern\u00e1ndez, L.F.: Stability of internal states in recurrent neural networks trained on regular languages. Neurocomputing 452, 212\u2013223 (2021). https:\/\/doi.org\/10.1016\/j.neucom.2021.04.058","journal-title":"Neurocomputing"},{"key":"1160_CR28","doi-asserted-by":"crossref","unstructured":"Muskardin, E., Aichernig, B.K., Pill, I., Tappler, M.: Learning finite state models from recurrent neural networks. In: IFM. LNCS, vol. 13274, pp. 229\u2013248. Springer, Cham (2022)","DOI":"10.1007\/978-3-031-07727-2_13"},{"issue":"3","key":"1160_CR29","doi-asserted-by":"publisher","first-page":"511","DOI":"10.1109\/72.286928","volume":"5","author":"MW Goudreau","year":"1994","unstructured":"Goudreau, M.W., Giles, C.L., Chakradhar, S.T., Chen, D.: First-order versus second-order single-layer recurrent neural networks. IEEE Trans. Neural Netw. 5(3), 511\u2013513 (1994). https:\/\/doi.org\/10.1109\/72.286928","journal-title":"IEEE Trans. Neural Netw."},{"key":"1160_CR30","doi-asserted-by":"publisher","unstructured":"Pferscher, A., Aichernig, B.K.: Fingerprinting Bluetooth Low Energy devices via active automata learning. In: FM. LNCS, vol. 13047, pp. 524\u2013542. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-90870-6_28","DOI":"10.1007\/978-3-030-90870-6_28"},{"key":"1160_CR31","doi-asserted-by":"publisher","unstructured":"Dong, G., Wang, J., Sun, J., Zhang, Y., Wang, X., Dai, T., Dong, J.S., Wang, X.: Towards interpreting recurrent neural networks through probabilistic abstraction. In: ASE, pp. 499\u2013510. IEEE (2020). https:\/\/doi.org\/10.1145\/3324884.3416592","DOI":"10.1145\/3324884.3416592"},{"key":"1160_CR32","doi-asserted-by":"publisher","unstructured":"Carrasco, R.C., Oncina, J.: Learning stochastic regular grammars by means of a state merging method. In: Carrasco, R.C., Oncina, J. (eds.) Grammatical Inference and Applications, Second International Colloquium, ICGI-94, Alicante, Spain, September 21\u201323, 1994, Proceedings. Lecture Notes in Computer Science, vol. 862, pp. 139\u2013152. Springer, Berlin (1994). https:\/\/doi.org\/10.1007\/3-540-58473-0_144","DOI":"10.1007\/3-540-58473-0_144"},{"key":"1160_CR33","doi-asserted-by":"publisher","unstructured":"Verwer, S., Hammerschmidt, C.A.: flexfringe: a passive automaton learning package. In: 2017 IEEE International Conference on Software Maintenance and Evolution, ICSME 2017, Shanghai, China, September 17\u201322, 2017, pp. 638\u2013642. IEEE Computer Society (2017). https:\/\/doi.org\/10.1109\/ICSME.2017.58","DOI":"10.1109\/ICSME.2017.58"},{"key":"1160_CR34","doi-asserted-by":"publisher","unstructured":"Johnson, C.G.: Genetic programming with fitness based on model checking. In: Ebner, M., O\u2019Neill, M., Ek\u00e1rt, A., Vanneschi, L., Esparcia-Alc\u00e1zar, A. (eds.) Genetic Programming, 10th European Conference, EuroGP 2007, Valencia, Spain, April 11\u201313, 2007, Proceedings. Lecture Notes in Computer Science, vol. 4445, pp. 114\u2013124. Springer (2007). https:\/\/doi.org\/10.1007\/978-3-540-71605-1_11","DOI":"10.1007\/978-3-540-71605-1_11"},{"key":"1160_CR35","doi-asserted-by":"publisher","unstructured":"Lai, Z., Cheung, S.C., Jiang, Y.: Dynamic model learning using genetic algorithm under adaptive model checking framework. In: Sixth International Conference on Quality Software (QSIC 2006), 26\u201328 October 2006, Beijing, China, pp. 410\u2013417. IEEE Computer Society (2006). https:\/\/doi.org\/10.1109\/QSIC.2006.25","DOI":"10.1109\/QSIC.2006.25"},{"key":"1160_CR36","doi-asserted-by":"publisher","unstructured":"Lefticaru, R., Ipate, F., Tudose, C.: Automated model design using genetic algorithms and model checking. In: Kefalas, P., Stamatis, D., Douligeris, C. (eds.) 2009 Fourth Balkan Conference in Informatics, BCI 2009, Thessaloniki, Greece, 17\u201319 September 2009, pp. 79\u201384. IEEE Computer Society (2009). https:\/\/doi.org\/10.1109\/BCI.2009.15","DOI":"10.1109\/BCI.2009.15"},{"key":"1160_CR37","doi-asserted-by":"crossref","unstructured":"Tappler, M., Aichernig, B.K., Larsen, K.G., Lorber, F.: Time to learn - learning timed automata from tests. In: Andr\u00e9, \u00c9., Stoelinga, M. (eds.) Formal Modeling and Analysis of Timed Systems\u201417th International Conference, FORMATS 2019, Amsterdam, The Netherlands, August 27\u201329, 2019, Proceedings. Lecture Notes in Computer Science, vol. 11750, pp. 216\u2013235. Springer (2019). 10.1007\/978-3-030-29662-9_13","DOI":"10.1007\/978-3-030-29662-9_13"},{"key":"1160_CR38","volume-title":"Representation of Events in Nerve Nets and Finite Automata","author":"SC Kleene","year":"1951","unstructured":"Kleene, S.C.: Representation of Events in Nerve Nets and Finite Automata. RAND Corporation, Santa Monica (1951)"},{"key":"1160_CR39","volume-title":"Computation: Finite and Infinite Machines","author":"ML Minsky","year":"1967","unstructured":"Minsky, M.L.: Computation: Finite and Infinite Machines. Prentice-Hall Inc, Hoboken (1967)"},{"key":"1160_CR40","unstructured":"Hinton, G.E., Vinyals, O., Dean, J.: Distilling the knowledge in a neural network. In: CoRR (2015). arXiv:1503.02531"},{"issue":"3","key":"1160_CR41","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1162\/NECO.1992.4.3.393","volume":"4","author":"CL Giles","year":"1992","unstructured":"Giles, C.L., Miller, C.B., Chen, D., Chen, H., Sun, G., Lee, Y.: Learning and extracting finite state automata with second-order recurrent neural networks. Neural Comput. 4(3), 393\u2013405 (1992). https:\/\/doi.org\/10.1162\/NECO.1992.4.3.393","journal-title":"Neural Comput."},{"issue":"1","key":"1160_CR42","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/0893-6080(95)00086-0","volume":"9","author":"CW Omlin","year":"1996","unstructured":"Omlin, C.W., Giles, C.L.: Extraction of rules from discrete-time recurrent neural networks. Neural Netw. 9(1), 41\u201352 (1996). https:\/\/doi.org\/10.1016\/0893-6080(95)00086-0","journal-title":"Neural Netw."},{"key":"1160_CR43","unstructured":"Wang, Q., Zhang, K., Liu, X., Giles, C.L.: Verification of recurrent neural networks through rule extraction. In: CoRR. (2018) arXiv:1811.06029"},{"key":"1160_CR44","doi-asserted-by":"publisher","unstructured":"Wang, Q., Zhang, K., II., A.G.O., Xing, X., Liu, X., Giles, C.L.: An empirical evaluation of rule extraction from recurrent neural networks. Neural Comput. 30(9), 2568\u20132591 (2018). https:\/\/doi.org\/10.1162\/NECO_A_01111","DOI":"10.1162\/NECO_A_01111"},{"issue":"4","key":"1160_CR45","doi-asserted-by":"publisher","first-page":"822","DOI":"10.1162\/neco.1995.7.4.822","volume":"7","author":"P Tino","year":"1995","unstructured":"Tino, P., Sajda, J.: Learning and extracting initial Mealy automata with a modular neural network model. Neural Comput. 7(4), 822\u2013844 (1995). https:\/\/doi.org\/10.1162\/neco.1995.7.4.822","journal-title":"Neural Comput."},{"key":"1160_CR46","unstructured":"Michalenko, J.J., Shah, A., Verma, A., Baraniuk, R.G., Chaudhuri, S., Patel, A.B.: Representing formal languages: a comparison between finite automata and recurrent neural networks. In: ICLR. OpenReview.net (2019)"},{"key":"1160_CR47","doi-asserted-by":"publisher","unstructured":"Hong, D., Segre, A.M., Wang, T.: Adaax: explaining recurrent neural networks by learning automata with adaptive states. In: Zhang, A., Rangwala, H. (eds.) KDD \u201922: The 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA, August 14\u201318, 2022, pp. 574\u2013584. ACM (2022). https:\/\/doi.org\/10.1145\/3534678.3539356","DOI":"10.1145\/3534678.3539356"},{"key":"1160_CR48","unstructured":"Weiss, G., Goldberg, Y., Yahav, E.: Learning deterministic weighted automata with queries and counterexamples. In: NeurIPS, pp. 8558\u20138569 (2019)"},{"key":"1160_CR49","doi-asserted-by":"publisher","unstructured":"Yellin, D.M., Weiss, G.: Synthesizing context-free grammars from recurrent neural networks. In: TACAS. LNCS, vol. 12651, pp. 351\u2013369. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-72016-2_19","DOI":"10.1007\/978-3-030-72016-2_19"},{"key":"1160_CR50","doi-asserted-by":"publisher","unstructured":"Mayr, F., Yovine, S.: Regular inference on artificial neural networks. In: CD-MAKE. LNCS, vol. 11015, pp. 350\u2013369. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99740-7_25","DOI":"10.1007\/978-3-319-99740-7_25"},{"key":"1160_CR51","doi-asserted-by":"publisher","unstructured":"Khmelnitsky, I., Neider, D., Roy, R., Xie, X., Barbot, B., Bollig, B., Finkel, A., Haddad, S., Leucker, M., Ye, L.: Property-directed verification and robustness certification of recurrent neural networks. In: ATVA. LNCS, vol. 12971, pp. 364\u2013380. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-88885-5_24","DOI":"10.1007\/978-3-030-88885-5_24"},{"key":"1160_CR52","unstructured":"Barbot, B., Bollig, B., Finkel, A., Haddad, S., Khmelnitsky, I., Leucker, M., Neider, D., Roy, R., Ye, L.: Extracting context-free grammars from recurrent neural networks using tree-automata learning and A* search. In: Chandlee, J., Eyraud, R., Heinz, J., Jardine, A., van Zaanen, M. (eds.) Proceedings of the 15th International Conference on Grammatical Inference, 23\u201327 August 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 153, pp. 113\u2013129. PMLR (2021). https:\/\/proceedings.mlr.press\/v153\/barbot21a.html"},{"key":"1160_CR53","unstructured":"Berstel, J., Reutenauer, C.: Rational series and their languages. In: EATCS Monographs on Theoretical Computer Science, vol. 12. Springer (1988). https:\/\/www.worldcat.org\/oclc\/17841475"},{"key":"1160_CR54","doi-asserted-by":"crossref","unstructured":"Eyraud, R., Ayache, S.: Distillation of weighted automata from recurrent neural networks using a spectral approach. In: CoRR (2020). arXiv:2009.13101","DOI":"10.1007\/s10994-021-05948-1"},{"key":"1160_CR55","unstructured":"Lacroce, C., Panangaden, P., Rabusseau, G.: Extracting weighted automata for approximate minimization in language modelling. In: Chandlee, J., Eyraud, R., Heinz, J., Jardine, A., van Zaanen, M. (eds.) Proceedings of the 15th International Conference on Grammatical Inference, 23\u201327 August 2021, Virtual Event. Proceedings of Machine Learning Research, vol. 153, pp. 92\u2013112. PMLR (2021). https:\/\/proceedings.mlr.press\/v153\/lacroce21a.html"},{"key":"1160_CR56","unstructured":"Eyraud, R., Lambert, D., Joutei, B.T., Gaffarov, A., Cabanne, M., Heinz, J., Shibata, C.: TAYSIR competition: transformer+RNN: algorithms to yield simple and interpretable representations. In: Coste, F., Ouardi, F., Rabusseau, G. (eds.) International Conference on Grammatical Inference, ICGI 2023, 10\u201313 July 2023, Rabat, Morocco. Proceedings of Machine Learning Research, vol. 217, pp. 275\u2013290. PMLR (2023). https:\/\/proceedings.mlr.press\/v217\/eyraud23a.html"},{"key":"1160_CR57","unstructured":"Muskardin, E., Tappler, M., Aichernig, B.K.: Testing-based black-box extraction of simple models from RNNs and transformers. In: Coste, F., Ouardi, F., Rabusseau, G. (eds.) International Conference on Grammatical Inference, ICGI 2023, 10\u201313 July 2023, Rabat, Morocco. Proceedings of Machine Learning Research, vol. 217, pp. 291\u2013294. PMLR (2023). https:\/\/proceedings.mlr.press\/v217\/muskardin23a.html"},{"key":"1160_CR58","unstructured":"Koul, A., Fern, A., Greydanus, S.: Learning finite state representations of recurrent policy networks. In: ICLR. OpenReview.net (2019)"},{"key":"1160_CR59","doi-asserted-by":"publisher","unstructured":"Carr, S., Jansen, N., Topcu, U.: Verifiable RNN-based policies for POMDPs under temporal logic constraints. In: IJCAI, pp. 4121\u20134127. ijcai.org (2020). https:\/\/doi.org\/10.24963\/ijcai.2020\/570","DOI":"10.24963\/ijcai.2020\/570"}],"container-title":["Software and Systems Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10270-024-01160-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10270-024-01160-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10270-024-01160-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,20]],"date-time":"2024-07-20T04:16:53Z","timestamp":1721449013000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10270-024-01160-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,21]]},"references-count":59,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,6]]}},"alternative-id":["1160"],"URL":"https:\/\/doi.org\/10.1007\/s10270-024-01160-6","relation":{},"ISSN":["1619-1366","1619-1374"],"issn-type":[{"value":"1619-1366","type":"print"},{"value":"1619-1374","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,21]]},"assertion":[{"value":"17 February 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 March 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}