{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T16:08:35Z","timestamp":1759334915513,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031975363"},{"type":"electronic","value":"9783031975370"}],"license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-031-97537-0_16","type":"book-chapter","created":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T22:50:10Z","timestamp":1759272610000},"page":"264-287","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Identification of\u00a0Classification Clusters in\u00a0Convolutional Neural Networks"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-5055-3761","authenticated-orcid":false,"given":"Felix","family":"Br\u00fcning","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5845-5840","authenticated-orcid":false,"given":"Felix","family":"H\u00f6fer","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9915-5357","authenticated-orcid":false,"given":"Wen-ling","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3667-9775","authenticated-orcid":false,"given":"Jan","family":"Peleska","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,1]]},"reference":[{"key":"16_CR1","unstructured":"Abadi, M., et al.: TensorFlow: Large-scale machine learning on heterogeneous systems (2015). https:\/\/www.tensorflow.org\/, software available from tensorflow.org"},{"key":"16_CR2","unstructured":"Aggarwal, C.C.: Neural Networks and Deep Learning. Springer Nature Switzerland AG, Cham, Switzerland (2018)"},{"key":"16_CR3","doi-asserted-by":"publisher","unstructured":"Akai, N., Hirayama, T., Murase, H.: Experimental stability analysis of neural networks in classification problems with confidence sets for persistence diagrams. Neural Netw. 143, 42\u201351 (2021). https:\/\/doi.org\/10.1016\/j.neunet.2021.05.007,https:\/\/doi.org\/10.1016\/j.neunet.2021.05.007","DOI":"10.1016\/j.neunet.2021.05.007"},{"key":"16_CR4","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.inffus.2021.07.015","volume":"77","author":"CJ Anders","year":"2022","unstructured":"Anders, C.J., Weber, L., Neumann, D., Samek, W., M\u00fcller, K.R., Lapuschkin, S.: Finding and removing clever Hans: using explanation methods to debug and improve deep models. Inform. Fusion 77, 261\u2013295 (2022). https:\/\/doi.org\/10.1016\/j.inffus.2021.07.015","journal-title":"Inform. Fusion"},{"key":"16_CR5","unstructured":"Apostol, T.M.: Mathematical Analysis. Addison-Wesley Publishing Company, reading, Massachusetts, second edn. (1974)"},{"key":"16_CR6","doi-asserted-by":"publisher","unstructured":"Benfenati, A., Marta, A.: A singular Riemannian geometry approach to deep neural networks i. theoretical foundations. Neural Netw. 158, 331\u2013343 (2023). https:\/\/doi.org\/10.1016\/j.neunet.2022.11.022","DOI":"10.1016\/j.neunet.2022.11.022"},{"key":"16_CR7","doi-asserted-by":"publisher","unstructured":"Benfenati, A., Marta, A.: A singular Riemannian geometry approach to deep neural networks ii. reconstruction of 1-d equivalence classes. Neural Netw. 158, 344\u2013358 (2023). https:\/\/doi.org\/10.1016\/j.neunet.2022.11.026","DOI":"10.1016\/j.neunet.2022.11.026"},{"key":"16_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1007\/978-3-319-66284-8_26","volume-title":"Computer Safety, Reliability, and Security","author":"N Bhardwaj","year":"2017","unstructured":"Bhardwaj, N., Liggesmeyer, P.: A runtime risk assessment concept for safe reconfiguration in open adaptive systems. In: Tonetta, S., Schoitsch, E., Bitsch, F. (eds.) SAFECOMP 2017. LNCS, vol. 10489, pp. 309\u2013316. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-66284-8_26"},{"key":"16_CR9","unstructured":"Braband, J., Lindner, L., Rexin, F.: Risk analyses for obstacle detection in automatic driving. SIGNAL+DRAHT 115(3), 12\u201320 (2023)"},{"key":"16_CR10","unstructured":"Chockler, H., Kroening, D., Sun, Y.: Compositional Explanations for Image Classifiers. arXiv:2103.03622 [cs] (2021). http:\/\/arxiv.org\/abs\/2103.03622, arXiv: 2103.03622"},{"key":"16_CR11","unstructured":"Chollet, F., et\u00a0al.: Keras. https:\/\/keras.io (2015)"},{"issue":"3","key":"16_CR12","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1016\/0166-218X(92)90177-C","volume":"39","author":"P Flajolet","year":"1992","unstructured":"Flajolet, P., Gardy, D., Thimonier, L.: Birthday paradox, coupon collectors, caching algorithms and self-organizing search. Discret. Appl. Math. 39(3), 207\u2013229 (1992). https:\/\/doi.org\/10.1016\/0166-218X(92)90177-C","journal-title":"Discret. Appl. Math."},{"key":"16_CR13","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1016\/j.future.2020.06.036","volume":"112","author":"F Flammini","year":"2020","unstructured":"Flammini, F., Marrone, S., Nardone, R., Caporuscio, M., D\u2019Angelo, M.: Safety integrity through self-adaptation for multi-sensor event detection: methodology and case-study. Futur. Gener. Comput. Syst. 112, 965\u2013981 (2020). https:\/\/doi.org\/10.1016\/j.future.2020.06.036","journal-title":"Futur. Gener. Comput. Syst."},{"key":"16_CR14","doi-asserted-by":"publisher","unstructured":"Gleirscher, M., Haxthausen, A.E., Peleska, J.: Probabilistic risk assessment of an obstacle detection system for goa 4 freight trains. In: Proceedings of the 9th ACM SIGPLAN International Workshop on Formal Techniques for Safety-Critical Systems, pp. 26\u201336. FTSCS 2023, Association for Computing Machinery, New York, NY, USA (2023). https:\/\/doi.org\/10.1145\/3623503.3623533","DOI":"10.1145\/3623503.3623533"},{"key":"16_CR15","doi-asserted-by":"publisher","unstructured":"Gruteser, J., Gele\u00dfus, D., Leuschel, M., Ro\u00dfbach, J., Vu, F.: A formal model of train control with AI-based obstacle detection. In: Milius, B., Dutilleul, S.C., Lecomte, T. (eds.) Reliability, Safety, and Security of Railway Systems. Modelling, Analysis, Verification, and Certification - 5th International Conference, RSSRail 2023, Berlin, Germany, October 10-12, 2023, Proceedings. Lecture Notes in Computer Science, vol. 14198, pp. 128\u2013145. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-43366-5_8","DOI":"10.1007\/978-3-031-43366-5_8"},{"issue":"3","key":"16_CR16","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/s10009-014-0356-8","volume":"18","author":"W Huang","year":"2014","unstructured":"Huang, W., Peleska, J.: Complete model-based equivalence class testing. Int. J. Softw. Tools Technol. Transfer 18(3), 265\u2013283 (2014). https:\/\/doi.org\/10.1007\/s10009-014-0356-8","journal-title":"Int. J. Softw. Tools Technol. Transfer"},{"key":"16_CR17","unstructured":"ISO: ISO\/DIS\u00a021448: Road vehicles \u2014 Safety of the intended functionality. European Committee for Electronic Standardization (2021). iCS: 43.040.10, Draft International Standard"},{"key":"16_CR18","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Bengio, Y., LeCun, Y. (eds.) 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings (2015). http:\/\/arxiv.org\/abs\/1412.6980"},{"key":"16_CR19","doi-asserted-by":"publisher","unstructured":"Kupeli, D.N.: Singular Semi-Riemannian Geometry. Springer Science+Business Media Dordrecht (1996). https:\/\/doi.org\/10.1007\/978-94-015-8761-7","DOI":"10.1007\/978-94-015-8761-7"},{"key":"16_CR20","unstructured":"LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database. ATT Labs. http:\/\/yann.lecun.com\/exdb\/mnist2 (2010)"},{"key":"16_CR21","doi-asserted-by":"publisher","unstructured":"Peleska, J., Haxthausen, A.E., Lecomte, T.: Standardisation considerations for autonomous train control. In: Margaria, T., Steffen, B. (eds.) Leveraging Applications of Formal Methods, Verification and Validation. Practice - 11th International Symposium, ISoLA 2022, Rhodes, Greece, October 22-30, 2022, Proceedings, Part IV. Lecture Notes in Computer Science, vol. 13704, pp. 286\u2013307. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19762-8_22","DOI":"10.1007\/978-3-031-19762-8_22"},{"key":"16_CR22","doi-asserted-by":"publisher","unstructured":"Risti\u0107-Durrant, D., Franke, M., Michels, K.: A review of vision-based on-board obstacle detection and distance estimation in railways. Sensors (Basel, Switzerland) 21(10), 3452 (2021). https:\/\/doi.org\/10.3390\/s21103452, https:\/\/www.ncbi.nlm.nih.gov\/pmc\/articles\/PMC8156009\/","DOI":"10.3390\/s21103452"},{"key":"16_CR23","doi-asserted-by":"publisher","unstructured":"Santos, C.F.G.D., Papa, J.P.: Avoiding overfitting: a survey on regularization methods for convolutional neural network. ACM Comput. Surv. 54(10s), 213:1\u2013213:25 (2022). https:\/\/doi.org\/10.1145\/3510413","DOI":"10.1145\/3510413"},{"key":"16_CR24","doi-asserted-by":"publisher","unstructured":"Sensoy, M., Saleki, M., Julier, S., Aydogan, R., Reid, J.: Misclassification risk and uncertainty quantification in deep classifiers. In: IEEE Winter Conference on Applications of Computer Vision, WACV 2021, Waikoloa, HI, USA, January 3-8, 2021, pp. 2483\u20132491. IEEE (2021). https:\/\/doi.org\/10.1109\/WACV48630.2021.00253","DOI":"10.1109\/WACV48630.2021.00253"},{"key":"16_CR25","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.procs.2018.05.198","volume":"132","author":"N Sharma","year":"2018","unstructured":"Sharma, N., Jain, V., Mishra, A.: An analysis of convolutional neural networks for image classification. Procedia Comput. Sci. 132, 377\u2013384 (2018). https:\/\/doi.org\/10.1016\/j.procs.2018.05.198","journal-title":"Procedia Comput. Sci."},{"key":"16_CR26","doi-asserted-by":"publisher","unstructured":"Shi, W., Alawieh, M.B., Li, X., Yu, H., Ar\u00e9chiga, N., Tomatsu, N.: Efficient statistical validation of machine learning systems for autonomous driving. In: Liu, F. (ed.) Proceedings of the 35th International Conference on Computer-Aided Design, ICCAD 2016, Austin, TX, USA, November 7-10, 2016, p.\u00a036. ACM (2016). https:\/\/doi.org\/10.1145\/2966986.2980077","DOI":"10.1145\/2966986.2980077"},{"key":"16_CR27","doi-asserted-by":"publisher","unstructured":"Sun, Y., Chockler, H., Huang, X., Kroening, D.: Explaining image classifiers using statistical fault localization. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J. (eds.) Computer Vision - ECCV 2020 - 16th European Conference, Glasgow, UK, August 23-28, 2020, Proceedings, Part XXVIII. Lecture Notes in Computer Science, vol. 12373, pp. 391\u2013406. Springer (2020). https:\/\/doi.org\/10.1007\/978-3-030-58604-1_24","DOI":"10.1007\/978-3-030-58604-1_24"},{"key":"16_CR28","doi-asserted-by":"publisher","unstructured":"Sun, Y., Wu, M., Ruan, W., Huang, X., Kwiatkowska, M., Kroening, D.: Concolic testing for deep neural networks. In: Huchard, M., K\u00e4stner, C., Fraser, G. (eds.) Proceedings of the 33rd ACM\/IEEE International Conference on Automated Software Engineering, ASE 2018, Montpellier, France, September 3-7, 2018, pp. 109\u2013119. ACM (2018). https:\/\/doi.org\/10.1145\/3238147.3238172","DOI":"10.1145\/3238147.3238172"},{"key":"16_CR29","unstructured":"Underwriters Laboratories Inc.: ANSI\/UL\u00a04600-2020 Standard for Evaluation of Autonomous Products \u2013 First Edition. Underwriters Laboratories Inc., 333 Pfingsten Road, Northbrook, Illinois 60062-2096, 847.272.8800 (2020)"}],"container-title":["Lecture Notes in Computer Science","Engineering Safe and Trustworthy Cyber Physical Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-97537-0_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T22:50:13Z","timestamp":1759272613000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-97537-0_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,1]]},"ISBN":["9783031975363","9783031975370"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-97537-0_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,10,1]]},"assertion":[{"value":"1 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}}]}}