{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T20:13:47Z","timestamp":1780344827183,"version":"3.54.1"},"reference-count":99,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T00:00:00Z","timestamp":1661731200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["1932723"],"award-info":[{"award-number":["1932723"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Glob Optim"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s10898-022-01228-x","type":"journal-article","created":{"date-parts":[[2022,8,29]],"date-time":"2022-08-29T03:16:42Z","timestamp":1661743002000},"page":"569-594","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Convex and concave envelopes of artificial neural network activation functions for deterministic global optimization"],"prefix":"10.1007","volume":"85","author":[{"given":"Matthew E.","family":"Wilhelm","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenyu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8435-9552","authenticated-orcid":false,"given":"Matthew D.","family":"Stuber","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,8,29]]},"reference":[{"issue":"11","key":"1228_CR1","doi-asserted-by":"publisher","first-page":"1054","DOI":"10.1016\/j.cep.2007.02.031","volume":"46","author":"O Kahrs","year":"2007","unstructured":"Kahrs, O., Marquardt, W.: The validity domain of hybrid models and its application in process optimization. Chem. Eng. Process. 46(11), 1054\u20131066 (2007). https:\/\/doi.org\/10.1016\/j.cep.2007.02.031","journal-title":"Chem. Eng. Process."},{"issue":"5","key":"1228_CR2","doi-asserted-by":"publisher","first-page":"1216","DOI":"10.1002\/aic.12341","volume":"57","author":"CA Henao","year":"2010","unstructured":"Henao, C.A., Maravelias, C.T.: Surrogate-based superstructure optimization framework. AIChE J. 57(5), 1216\u20131232 (2010). https:\/\/doi.org\/10.1002\/aic.12341","journal-title":"AIChE J."},{"issue":"3","key":"1228_CR3","doi-asserted-by":"publisher","first-page":"925","DOI":"10.1007\/s10957-018-1396-0","volume":"180","author":"AM Schweidtmann","year":"2018","unstructured":"Schweidtmann, A.M., Mitsos, A.: Deterministic global optimization with artificial neural networks embedded. J. Optim. Theory Appl. 180(3), 925\u2013948 (2018). https:\/\/doi.org\/10.1007\/s10957-018-1396-0","journal-title":"J. Optim. Theory Appl."},{"key":"1228_CR4","doi-asserted-by":"publisher","first-page":"514","DOI":"10.5555\/2998828.2998901","volume":"8","author":"C Williams","year":"1995","unstructured":"Williams, C., Rasmussen, C.: Gaussian processes for regression. Adv. Neural. Inf. Process. Syst. 8, 514\u2013520 (1995). https:\/\/doi.org\/10.5555\/2998828.2998901","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"10","key":"1228_CR5","doi-asserted-by":"publisher","first-page":"2633","DOI":"10.1002\/aic.11579","volume":"54","author":"JA Caballero","year":"2008","unstructured":"Caballero, J.A., Grossmann, I.E.: An algorithm for the use of surrogate models in modular flowsheet optimization. AIChE J. 54(10), 2633\u20132650 (2008). https:\/\/doi.org\/10.1002\/aic.11579","journal-title":"AIChE J."},{"issue":"3","key":"1228_CR6","doi-asserted-by":"publisher","first-page":"553","DOI":"10.1007\/s12532-021-00204-y","volume":"13","author":"AM Schweidtmann","year":"2021","unstructured":"Schweidtmann, A.M., Bongartz, D., Grothe, D., Kerkenhoff, T., Lin, X., Najman, J., Mitsos, A.: Deterministic global optimization with gaussian processes embedded. Math. Program. Comput. 13(3), 553\u2013581 (2021). https:\/\/doi.org\/10.1007\/s12532-021-00204-y","journal-title":"Math. Program. Comput."},{"key":"1228_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-021-09608-0","author":"AM Schweidtmann","year":"2021","unstructured":"Schweidtmann, A.M., Weber, J.M., Wende, C., Netze, L., Mitsos, A.: Obey validity limits of data-driven models through topological data analysis and one-class classification. Optim. Eng. (2021). https:\/\/doi.org\/10.1007\/s11081-021-09608-0","journal-title":"Optim. Eng."},{"key":"1228_CR8","unstructured":"Abadi, M., Agarwal, A., Barham, P., Brevdo, E., Chen, Z., Citro, C., Corrado, G.S., Davis, A., Dean, J., Devin, M., Ghemawat, S., Goodfellow, I., Harp, A., Irving, G., Isard, M., Jia, Y., Jozefowicz, R., Kaiser, L., Kudlur, M., Levenberg, J., Man\u00e9, D., Monga, R., Moore, S., Murray, D., Olah, C., Schuster, M., Shlens, J., Steiner, B., Sutskever, I., Talwar, K., Tucker, P., Vanhoucke, V., Vasudevan, V., Vi\u00e9gas, F., Vinyals, O., Warden, P., Wattenberg, M., Wicke, M., Yu, Y., Zheng, X.: TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems. Software available from tensorflow.org (2015). https:\/\/www.tensorflow.org\/"},{"key":"1228_CR9","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: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019 Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems 32 (NeurIPS 2019), pp. 8024\u20138035. Curran Associates, Inc., Vancouver (2019)"},{"key":"1228_CR10","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.compchemeng.2012.06.006","volume":"46","author":"I Fahmi","year":"2012","unstructured":"Fahmi, I., Cremaschi, S.: Process synthesis of biodiesel production plant using artificial neural networks as the surrogate models. Comput. Chem. Eng. 46, 105\u2013123 (2012). https:\/\/doi.org\/10.1016\/j.compchemeng.2012.06.006","journal-title":"Comput. Chem. Eng."},{"issue":"21","key":"1228_CR11","doi-asserted-by":"publisher","first-page":"1837","DOI":"10.1023\/a:1026225526558","volume":"25","author":"Y Nagata","year":"2003","unstructured":"Nagata, Y., Chu, K.H.: Optimization of a fermentation medium using neural networks and genetic algorithms. Biotech. Lett. 25(21), 1837\u20131842 (2003). https:\/\/doi.org\/10.1023\/a:1026225526558","journal-title":"Biotech. Lett."},{"key":"1228_CR12","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.compchemeng.2017.05.006","volume":"104","author":"HRS Anna","year":"2017","unstructured":"Anna, H.R.S., Barreto, A.G., Tavares, F.W., de Souza, M.B.: Machine learning model and optimization of a PSA unit for methane-nitrogen separation. Comput. Chem. Eng. 104, 377\u2013391 (2017). https:\/\/doi.org\/10.1016\/j.compchemeng.2017.05.006","journal-title":"Comput. Chem. Eng."},{"issue":"3","key":"1228_CR13","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1016\/s0023-6438(95)94364-1","volume":"28","author":"M Dornier","year":"1995","unstructured":"Dornier, M., Decloux, M., Trystram, G., Lebert, A.M.: Interest of neural networks for the optimization of the crossflow filtration process. LWT Food Sci. Technol. 28(3), 300\u2013309 (1995). https:\/\/doi.org\/10.1016\/s0023-6438(95)94364-1","journal-title":"LWT Food Sci. Technol."},{"key":"1228_CR14","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1016\/s0098-1354(98)00105-7","volume":"22","author":"CAO Nascimento","year":"1998","unstructured":"Nascimento, C.A.O., Giudici, R.: Neural network based approach for optimisation applied to an industrial nylon-6,6 polymerisation process. Comput. Chem. Eng. 22, 595\u2013600 (1998). https:\/\/doi.org\/10.1016\/s0098-1354(98)00105-7","journal-title":"Comput. Chem. Eng."},{"issue":"1","key":"1228_CR15","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/s0954-1810(98)00011-9","volume":"13","author":"MA Hussain","year":"1999","unstructured":"Hussain, M.A.: Review of the applications of neural networks in chemical process control\u2014simulation and online implementation. Artif. Intell. Eng. 13(1), 55\u201368 (1999). https:\/\/doi.org\/10.1016\/s0954-1810(98)00011-9","journal-title":"Artif. Intell. Eng."},{"issue":"3","key":"1228_CR16","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1002\/aic.16497","volume":"65","author":"M Onel","year":"2019","unstructured":"Onel, M., Kieslich, C.A., Pistikopoulos, E.N.: A nonlinear support vector machine-based feature selection approach for fault detection and diagnosis: application to the tennessee eastman process. AIChE J. 65(3), 992\u20131005 (2019). https:\/\/doi.org\/10.1002\/aic.16497","journal-title":"AIChE J."},{"issue":"4","key":"1228_CR17","doi-asserted-by":"publisher","first-page":"968","DOI":"10.3390\/en13040968","volume":"13","author":"Y Seong","year":"2020","unstructured":"Seong, Y., Park, C., Choi, J., Jang, I.: Surrogate model with a deep neural network to evaluate gas\u2013liquid flow in a horizontal pipe. Energies 13(4), 968 (2020). https:\/\/doi.org\/10.3390\/en13040968","journal-title":"Energies"},{"key":"1228_CR18","doi-asserted-by":"publisher","unstructured":"Villmann, T., Ravichandran, J., Villmann, A., Nebel, D., Kaden, M.: Investigation of activation functions for generalized learning vector quantization. In: International Workshop on Self-Organizing Maps, pp. 179\u2013188. Springer, Berlin (2019). https:\/\/doi.org\/10.1007\/978-3-030-19642-4_18","DOI":"10.1007\/978-3-030-19642-4_18"},{"key":"1228_CR19","doi-asserted-by":"publisher","unstructured":"Xu, L., Chen, C.P.: Comparison and combination of activation functions in broad learning system. In: 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC), pp. 3537\u20133542 (2020). https:\/\/doi.org\/10.1109\/SMC42975.2020.9282871","DOI":"10.1109\/SMC42975.2020.9282871"},{"key":"1228_CR20","doi-asserted-by":"publisher","unstructured":"Nader, A., Azar, D.: Searching for activation functions using a self-adaptive evolutionary algorithm. In: Proceedings of the 2020 Genetic and Evolutionary Computation Conference Companion, pp. 145\u2013146 (2020). https:\/\/doi.org\/10.1145\/3377929.3389942","DOI":"10.1145\/3377929.3389942"},{"key":"1228_CR21","doi-asserted-by":"publisher","unstructured":"Cristina, G.N.M., Sanchez, V.G.C., Villegas, O.O.V., Nandayapa, M., Dominguez, H.d.J.O., Azuela, J.H.S.: Study of the effect of combining activation functions in a convolutional neural network. IEEE Lat. Am. Trans. 19(5), 844\u2013852 (2021). https:\/\/doi.org\/10.1109\/TLA.2021.9448319","DOI":"10.1109\/TLA.2021.9448319"},{"issue":"3","key":"1228_CR22","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1007\/s10601-018-9285-6","volume":"23","author":"M Fischetti","year":"2018","unstructured":"Fischetti, M., Jo, J.: Deep neural networks and mixed integer linear optimization. Constraints 23(3), 296\u2013309 (2018)","journal-title":"Constraints"},{"key":"1228_CR23","doi-asserted-by":"crossref","unstructured":"Anderson, R., Huchette, J., Ma, W., Tjandraatmadja, C., Vielma, J.P.: Strong mixed-integer programming formulations for trained neural networks. Math. Program. 1\u201337 (2020)","DOI":"10.1007\/s10107-020-01474-5"},{"key":"1228_CR24","doi-asserted-by":"crossref","unstructured":"Kronqvist, J., Misener, R., Tsay, C.: Between steps: Intermediate relaxations between big-m and convex hull formulations. In: International Conference on Integration of Constraint Programming, Artificial Intelligence, and Operations Research, pp. 299\u2013314. Springer, Berlin (2021)","DOI":"10.1007\/978-3-030-78230-6_19"},{"key":"1228_CR25","unstructured":"Tsay, C., Kronqvist, J., Thebelt, A., Misener, R.: Partition-based formulations for mixed-integer optimization of trained ReLU neural networks. In: Advances in Neural Information Processing Systems, vol. 34 (2021)"},{"key":"1228_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2019.106580","volume":"131","author":"B Grimstad","year":"2019","unstructured":"Grimstad, B., Andersson, H.: ReLU networks as surrogate models in mixed-integer linear programs. Comput. Chem. Eng. 131, 106580 (2019). https:\/\/doi.org\/10.1016\/j.compchemeng.2019.106580","journal-title":"Comput. Chem. Eng."},{"key":"1228_CR27","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1016\/j.compchemeng.2018.10.007","volume":"121","author":"AM Schweidtmann","year":"2019","unstructured":"Schweidtmann, A.M., Huster, W.R., L\u00fcthje, J.T., Mitsos, A.: Deterministic global process optimization: Accurate (single-species) properties via artificial neural networks. Comput. Chem. Eng. 121, 67\u201374 (2019). https:\/\/doi.org\/10.1016\/j.compchemeng.2018.10.007","journal-title":"Comput. Chem. Eng."},{"key":"1228_CR28","doi-asserted-by":"publisher","unstructured":"Moore, R.E., Kearfott, R.B., Cloud, M.J.: Introduction to Interval Analysis. SIAM, Philadelpha (2009). https:\/\/doi.org\/10.1137\/1.9780898717716","DOI":"10.1137\/1.9780898717716"},{"issue":"5","key":"1228_CR29","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.compchemeng.2011.01.031","volume":"35","author":"AM Sahlodin","year":"2011","unstructured":"Sahlodin, A.M., Chachuat, B.: Convex\/concave relaxations of parametric odes using Taylor models. Comput. Chem. Eng. 35(5), 844\u2013857 (2011). https:\/\/doi.org\/10.1016\/j.compchemeng.2011.01.031","journal-title":"Comput. Chem. Eng."},{"issue":"1","key":"1228_CR30","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1007\/bf01580665","volume":"10","author":"GP McCormick","year":"1976","unstructured":"McCormick, G.P.: Computability of global solutions to factorable nonconvex programs: part I\u2014convex underestimating problems. Math. Program. 10(1), 147\u2013175 (1976). https:\/\/doi.org\/10.1007\/bf01580665","journal-title":"Math. Program."},{"issue":"4","key":"1228_CR31","doi-asserted-by":"publisher","first-page":"569","DOI":"10.1007\/s10898-011-9664-7","volume":"51","author":"JK Scott","year":"2011","unstructured":"Scott, J.K., Stuber, M.D., Barton, P.I.: Generalized McCormick relaxations. J. Global Optim. 51(4), 569\u2013606 (2011). https:\/\/doi.org\/10.1007\/s10898-011-9664-7","journal-title":"J. Global Optim."},{"issue":"2","key":"1228_CR32","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1137\/080717341","volume":"20","author":"A Mitsos","year":"2009","unstructured":"Mitsos, A., Chachuat, B., Barton, P.I.: McCormick-based relaxations of algorithms. SIAM J. Optim. 20(2), 573\u2013601 (2009). https:\/\/doi.org\/10.1137\/080717341","journal-title":"SIAM J. Optim."},{"issue":"3","key":"1228_CR33","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1080\/10556788.2014.924514","volume":"30","author":"MD Stuber","year":"2015","unstructured":"Stuber, M.D., Scott, J.K., Barton, P.I.: Convex and concave relaxations of implicit functions. Optim. Methods Softw. 30(3), 424\u2013460 (2015). https:\/\/doi.org\/10.1080\/10556788.2014.924514","journal-title":"Optim. Methods Softw."},{"key":"1228_CR34","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/0-306-48332-7_74","volume-title":"Encyclopedia of Optimization","author":"Y Yajima","year":"2001","unstructured":"Yajima, Y.: Convex envelopes in optimization problems: Convex envelopes in optimization problems. In: Floudas, C.A., Pardalos, P.M. (eds.) Encyclopedia of Optimization, pp. 343\u2013344. Springer, Boston (2001). https:\/\/doi.org\/10.1007\/0-306-48332-7_74"},{"key":"1228_CR35","doi-asserted-by":"publisher","unstructured":"Wilhelm, M.E., Gottlieb, R.X., Stuber, M.D.: PSORLab\/McCormick.jl. Zenodo (2020). https:\/\/doi.org\/10.5281\/ZENODO.5749918. https:\/\/github.com\/PSORLab\/McCormick.jl","DOI":"10.5281\/ZENODO.5749918"},{"issue":"6","key":"1228_CR36","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1016\/S0893-6080(05)80125-X","volume":"6","author":"K-I Funahashi","year":"1993","unstructured":"Funahashi, K.-I., Nakamura, Y.: Approximation of dynamical systems by continuous time recurrent neural networks. Neural Netw. 6(6), 801\u2013806 (1993). https:\/\/doi.org\/10.1016\/S0893-6080(05)80125-X","journal-title":"Neural Netw."},{"issue":"1","key":"1228_CR37","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6420\/aa9a90","volume":"34","author":"E Haber","year":"2017","unstructured":"Haber, E., Ruthotto, L.: Stable architectures for deep neural networks. Inverse Prob. 34(1), 014004 (2017). https:\/\/doi.org\/10.1088\/1361-6420\/aa9a90","journal-title":"Inverse Prob."},{"key":"1228_CR38","unstructured":"Lu, Y., Zhong, A., Li, Q., Dong, B.: Beyond finite layer neural networks: Bridging deep architectures and numerical differential equations. In: International Conference on Machine Learning, pp. 3276\u20133285 (2018). PMLR"},{"issue":"3","key":"1228_CR39","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1007\/s10851-019-00903-1","volume":"62","author":"L Ruthotto","year":"2020","unstructured":"Ruthotto, L., Haber, E.: Deep neural networks motivated by partial differential equations. J. Math. Imaging Vis. 62(3), 352\u2013364 (2020). https:\/\/doi.org\/10.1007\/s10851-019-00903-1","journal-title":"J. Math. Imaging Vis."},{"key":"1228_CR40","doi-asserted-by":"publisher","unstructured":"Chen, R.T., Rubanova, Y., Bettencourt, J., Duvenaud, D.: Neural ordinary differential equations. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems, pp. 6572\u20136583 (2018). https:\/\/doi.org\/10.5555\/3327757.3327764","DOI":"10.5555\/3327757.3327764"},{"key":"1228_CR41","unstructured":"Rackauckas, C., Innes, M., Ma, Y., Bettencourt, J., White, L., Dixit, V.: Diffeqflux.jl\u2014A Julia library for neural differential equations. arXiv preprint arXiv:1902.02376 (2019)"},{"issue":"1","key":"1228_CR42","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1007\/s10898-012-9909-0","volume":"57","author":"JK Scott","year":"2013","unstructured":"Scott, J.K., Barton, P.I.: Improved relaxations for the parametric solutions of odes using differential inequalities. J. Global Optim. 57(1), 143\u2013176 (2013). https:\/\/doi.org\/10.1007\/s10898-012-9909-0","journal-title":"J. Global Optim."},{"issue":"2","key":"1228_CR43","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1002\/oca.2014","volume":"34","author":"JK Scott","year":"2013","unstructured":"Scott, J.K., Chachuat, B., Barton, P.I.: Nonlinear convex and concave relaxations for the solutions of parametric odes. Optimal Control Appl. Methods 34(2), 145\u2013163 (2013). https:\/\/doi.org\/10.1002\/oca.2014","journal-title":"Optimal Control Appl. Methods"},{"key":"1228_CR44","doi-asserted-by":"publisher","DOI":"10.1002\/aic.16836","author":"ME Wilhelm","year":"2019","unstructured":"Wilhelm, M.E., Le, A.V., Stuber, M.D.: Global optimization of stiff dynamical systems. AIChE J. (2019). https:\/\/doi.org\/10.1002\/aic.16836","journal-title":"AIChE J."},{"key":"1228_CR45","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-021-01654-x","author":"Y Song","year":"2021","unstructured":"Song, Y., Khan, K.A.: Optimization-based convex relaxations for nonconvex parametric systems of ordinary differential equations. Math. Program. (2021). https:\/\/doi.org\/10.1007\/s10107-021-01654-x","journal-title":"Math. Program."},{"issue":"3","key":"1228_CR46","doi-asserted-by":"publisher","first-page":"930","DOI":"10.1137\/20M1358517","volume":"3","author":"L El Ghaoui","year":"2021","unstructured":"El Ghaoui, L., Gu, F., Travacca, B., Askari, A., Tsai, A.: Implicit deep learning. SIAM J. Math. Data Sci. 3(3), 930\u2013958 (2021). https:\/\/doi.org\/10.1137\/20M1358517","journal-title":"SIAM J. Math. Data Sci."},{"key":"1228_CR47","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1016\/j.apenergy.2012.06.040","volume":"101","author":"AN Celik","year":"2013","unstructured":"Celik, A.N., Kolhe, M.: Generalized feed-forward based method for wind energy prediction. Appl. Energy 101, 582\u2013588 (2013). https:\/\/doi.org\/10.1016\/j.apenergy.2012.06.040","journal-title":"Appl. Energy"},{"key":"1228_CR48","unstructured":"Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of The Thirteenth International Conference on Artificial Intelligence and Statistics, pp. 249\u2013256 (2010). https:\/\/proceedings.mlr.press\/v9\/glorot10a.html"},{"issue":"1\u20133","key":"1228_CR49","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"G-B Huang","year":"2006","unstructured":"Huang, G.-B., Zhu, Q.-Y., Siew, C.-K.: Extreme learning machine: theory and applications. Neurocomputing 70(1\u20133), 489\u2013501 (2006). https:\/\/doi.org\/10.1016\/j.neucom.2005.12.126","journal-title":"Neurocomputing"},{"key":"1228_CR50","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1201\/9781003040620","volume-title":"Recurrent Neural Networks: Design and Applications","author":"L Medsker","year":"1999","unstructured":"Medsker, L., Jain, L.C.: Recurrent Neural Networks: Design and Applications, pp. 64\u201367. CRC Press, Boca Raton (1999). https:\/\/doi.org\/10.1201\/9781003040620"},{"key":"1228_CR51","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"1228_CR52","volume-title":"Global Optimization: Deterministic Approaches","author":"R Horst","year":"2013","unstructured":"Horst, R., Tuy, H.: Global Optimization: Deterministic Approaches. Springer, Berlin (2013)"},{"key":"1228_CR53","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1016\/b978-0-12-818634-3.50157-0","volume":"46","author":"AM Schweidtmann","year":"2019","unstructured":"Schweidtmann, A.M., Bongartz, D., Huster, W.R., Mitsos, A.: Deterministic global process optimization: Flash calculations via artificial neural networks. Comput. Aided Chem. Eng. 46, 937\u2013942 (2019). https:\/\/doi.org\/10.1016\/b978-0-12-818634-3.50157-0","journal-title":"Comput. Aided Chem. Eng."},{"key":"1228_CR54","unstructured":"Chachuat, B.C.: MC++: Toolkit for Construction, Manipulation and Bounding of Factorable Functions (2020). https:\/\/omega-icl.github.io\/mcpp\/"},{"issue":"6","key":"1228_CR55","doi-asserted-by":"publisher","first-page":"84","DOI":"10.1145\/3065386","volume":"60","author":"A Krizhevsky","year":"2017","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. Commun. ACM 60(6), 84\u201390 (2017). https:\/\/doi.org\/10.1145\/3065386","journal-title":"Commun. ACM"},{"issue":"5","key":"1228_CR56","doi-asserted-by":"publisher","first-page":"1671","DOI":"10.4208\/cicp.OA-2020-0165","volume":"28","author":"L Lu","year":"2020","unstructured":"Lu, L., Shin, Y., Su, Y., Karniadakis, G.E.: Dying ReLU and initialization: theory and numerical examples. Commun. Comput. Phys. 28(5), 1671\u20131706 (2020). https:\/\/doi.org\/10.4208\/cicp.OA-2020-0165","journal-title":"Commun. Comput. Phys."},{"key":"1228_CR57","unstructured":"Clevert, D.-A., Unterthiner, T., Hochreiter, S.: Fast and accurate deep network learning by exponential linear units (ELUs). arXiv preprint arXiv:1511.07289 (2015)"},{"key":"1228_CR58","doi-asserted-by":"publisher","unstructured":"Klambauer, G., Unterthiner, T., Mayr, A., Hochreiter, S.: Self-normalizing neural networks. In: Advances in Neural Information Processing Systems, pp. 971\u2013980 (2017). https:\/\/doi.org\/10.5555\/3294771.3294864","DOI":"10.5555\/3294771.3294864"},{"key":"1228_CR59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/10556788.2020.1786566","volume":"1","author":"ME Wilhelm","year":"2020","unstructured":"Wilhelm, M.E., Stuber, M.D.: EAGO.jl: easy advanced global optimization in Julia. Optim. Methods Softw. 1, 1\u201326 (2020). https:\/\/doi.org\/10.1080\/10556788.2020.1786566","journal-title":"Optim. Methods Softw."},{"issue":"1","key":"1228_CR60","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10898-011-9685-2","volume":"52","author":"A Bompadre","year":"2011","unstructured":"Bompadre, A., Mitsos, A.: Convergence rate of McCormick relaxations. J. Global Optim. 52(1), 1\u201328 (2011). https:\/\/doi.org\/10.1007\/s10898-011-9685-2","journal-title":"J. Global Optim."},{"issue":"3","key":"1228_CR61","doi-asserted-by":"publisher","first-page":"629","DOI":"10.1007\/s10898-017-0531-z","volume":"69","author":"R Kannan","year":"2017","unstructured":"Kannan, R., Barton, P.I.: The cluster problem in constrained global optimization. J. Global Optim. 69(3), 629\u2013676 (2017). https:\/\/doi.org\/10.1007\/s10898-017-0531-z","journal-title":"J. Global Optim."},{"issue":"2","key":"1228_CR62","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/bf00138689","volume":"8","author":"HS Ryoo","year":"1996","unstructured":"Ryoo, H.S., Sahinidis, N.V.: A branch-and-reduce approach to global optimization. J. Global Optim. 8(2), 107\u2013138 (1996). https:\/\/doi.org\/10.1007\/bf00138689","journal-title":"J. Global Optim."},{"issue":"2","key":"1228_CR63","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1007\/s10107-005-0581-8","volume":"103","author":"M Tawarmalani","year":"2005","unstructured":"Tawarmalani, M., Sahinidis, N.V.: A polyhedral branch-and-cut approach to global optimization. Math. Program. 103(2), 225\u2013249 (2005). https:\/\/doi.org\/10.1007\/s10107-005-0581-8","journal-title":"Math. Program."},{"key":"1228_CR64","doi-asserted-by":"publisher","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted boltzmann machines. In: ICML: Proceedings of the 27th International Conference on Machine Learning, pp. 807\u2013814 (2010). https:\/\/doi.org\/10.5555\/3104322.3104425","DOI":"10.5555\/3104322.3104425"},{"key":"1228_CR65","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 1026\u20131034. IEEE, Santiago, Chile (2015). https:\/\/doi.org\/10.1109\/iccv.2015.123","DOI":"10.1109\/iccv.2015.123"},{"key":"1228_CR66","doi-asserted-by":"publisher","unstructured":"Eger, S., Youssef, P., Gurevych, I.: Is it time to swish? Comparing deep learning activation functions across NLP tasks. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018). https:\/\/doi.org\/10.18653\/v1\/d18-1472","DOI":"10.18653\/v1\/d18-1472"},{"key":"1228_CR67","doi-asserted-by":"publisher","unstructured":"Zheng, H., Yang, Z., Liu, W., Liang, J., Li, Y.: Improving deep neural networks using softplus units. In: 2015 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20134 (2015). https:\/\/doi.org\/10.1109\/IJCNN.2015.7280459. IEEE","DOI":"10.1109\/IJCNN.2015.7280459"},{"key":"1228_CR68","unstructured":"Nwankpa, C.E., Ijomah, W., Gachagan, A., Marshall, S.: Activation functions: comparison of trends in practice and research for deep learning. In: 2nd International Conference on Computational Sciences and Technology, pp. 124\u2013133 (2021)"},{"issue":"5","key":"1228_CR69","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik, K., Stinchcombe, M., White, H.: Multilayer feedforward networks are universal approximators. Neural Netw. 2(5), 359\u2013366 (1989). https:\/\/doi.org\/10.1016\/0893-6080(89)90020-8","journal-title":"Neural Netw."},{"key":"1228_CR70","unstructured":"Elliott, D.L.: A better activation function for artificial neural networks. Technical report, Institute for Systems Research (1993). http:\/\/hdl.handle.net\/1903\/5355"},{"key":"1228_CR71","unstructured":"Sahlodin, A.M.: Global optimization of dynamic process systems using complete search methods. Ph.D. thesis, McMaster University (2013). https:\/\/macsphere.mcmaster.ca\/handle\/11375\/12803"},{"key":"1228_CR72","unstructured":"Hendrycks, D., Gimpel, K.: Gaussian error linear units (GELUs). arXiv preprint (2016) arXiv:1606.08415"},{"key":"1228_CR73","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1016\/j.neunet.2017.12.012","volume":"107","author":"S Elfwing","year":"2018","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw. 107, 3\u201311 (2018). https:\/\/doi.org\/10.1016\/j.neunet.2017.12.012","journal-title":"Neural Netw."},{"key":"1228_CR74","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1016\/j.neunet.2014.09.006","volume":"64","author":"S Elfwing","year":"2015","unstructured":"Elfwing, S., Uchibe, E., Doya, K.: Expected energy-based restricted Boltzmann machine for classification. Neural Netw. 64, 29\u201338 (2015). https:\/\/doi.org\/10.1016\/j.neunet.2014.09.006","journal-title":"Neural Netw."},{"key":"1228_CR75","unstructured":"Ramachandran, P., Zoph, B., Le, Q.V.: Searching for activation functions. arXiv preprint (2017) https:\/\/arxiv.org\/abs\/1710.05941"},{"key":"1228_CR76","unstructured":"Chen, J., Revels, J.: Robust benchmarking in noisy environments. arXiv e-prints arXiv:1608.04295 [cs.PF] (2016)"},{"issue":"4","key":"1228_CR77","doi-asserted-by":"publisher","first-page":"597","DOI":"10.1007\/s10898-016-0408-6","volume":"66","author":"J Najman","year":"2016","unstructured":"Najman, J., Mitsos, A.: Convergence analysis of multivariate McCormick relaxations. J. Global Optim. 66(4), 597\u2013628 (2016). https:\/\/doi.org\/10.1007\/s10898-016-0408-6","journal-title":"J. Global Optim."},{"issue":"3","key":"1228_CR78","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1007\/bf01096455","volume":"5","author":"K Du","year":"1994","unstructured":"Du, K., Kearfott, R.B.: The cluster problem in multivariate global optimization. J. Global Optim. 5(3), 253\u2013265 (1994). https:\/\/doi.org\/10.1007\/bf01096455","journal-title":"J. Global Optim."},{"issue":"3","key":"1228_CR79","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1007\/s10898-013-0059-9","volume":"58","author":"A Wechsung","year":"2014","unstructured":"Wechsung, A., Schaber, S.D., Barton, P.I.: The cluster problem revisited. J. Global Optim. 58(3), 429\u2013438 (2014). https:\/\/doi.org\/10.1007\/s10898-013-0059-9","journal-title":"J. Global Optim."},{"issue":"3","key":"1228_CR80","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1023\/A:1008212418949","volume":"11","author":"TGW Epperly","year":"1997","unstructured":"Epperly, T.G.W., Pistikopoulos, E.N.: A reduced space branch and bound algorithm for global optimization. J. Global Optim. 11(3), 287\u2013311 (1997). https:\/\/doi.org\/10.1023\/A:1008212418949","journal-title":"J. Global Optim."},{"key":"1228_CR81","doi-asserted-by":"publisher","unstructured":"Stuber, M.D.: Evaluation of process systems operating envelopes. Ph.D. thesis, Massachusetts Institute of Technology (2012). https:\/\/doi.org\/10.13140\/2.1.1775.4409","DOI":"10.13140\/2.1.1775.4409"},{"key":"1228_CR82","unstructured":"Wechsung, A.: Global optimization in reduced space. Ph.D. thesis, Massachusetts Institute of Technology (2014). https:\/\/dspace.mit.edu\/handle\/1721.1\/87131"},{"issue":"4","key":"1228_CR83","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1007\/s10898-017-0547-4","volume":"69","author":"D Bongartz","year":"2017","unstructured":"Bongartz, D., Mitsos, A.: Deterministic global optimization of process flowsheets in a reduced space using McCormick relaxations. J. Global Optim. 69(4), 761\u2013796 (2017). https:\/\/doi.org\/10.1007\/s10898-017-0547-4","journal-title":"J. Global Optim."},{"key":"1228_CR84","unstructured":"Sahinidis, N.V.: BARON 21.1.13: Global Optimization of Mixed-Integer Nonlinear Programs, User\u2019s Manual (2017). https:\/\/www.minlp.com\/downloads\/docs\/baron%20manual.pdf"},{"issue":"2\u20133","key":"1228_CR85","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s10898-014-0166-2","volume":"59","author":"R Misener","year":"2014","unstructured":"Misener, R., Floudas, C.A.: ANTIGONE: Algorithms for continuous\/integer global optimization of nonlinear equations. J. Global Optim. 59(2\u20133), 503\u2013526 (2014). https:\/\/doi.org\/10.1007\/s10898-014-0166-2","journal-title":"J. Global Optim."},{"key":"1228_CR86","unstructured":"Bongartz, D., Najman, J., Sass, S., Mitsos, A.: MAiNGO: McCormick based algorithm for mixed integer nonlinear global optimization. Process Systems Engineering (AVT. SVT), RWTH Aachen University (2018). https:\/\/git.rwth-aachen.de\/avt-svt\/public\/maingo"},{"issue":"3","key":"1228_CR87","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1007\/s10898-012-9905-4","volume":"56","author":"RB Kearfott","year":"2013","unstructured":"Kearfott, R.B., Castille, J., Tyagi, G.: A general framework for convexity analysis in deterministic global optimization. J. Global Optim. 56(3), 765\u2013785 (2013). https:\/\/doi.org\/10.1007\/s10898-012-9905-4","journal-title":"J. Global Optim."},{"issue":"4","key":"1228_CR88","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1007\/s10898-016-0440-6","volume":"67","author":"KA Khan","year":"2016","unstructured":"Khan, K.A., Watson, H.A.J., Barton, P.I.: Differentiable McCormick relaxations. J. Global Optim. 67(4), 687\u2013729 (2016). https:\/\/doi.org\/10.1007\/s10898-016-0440-6","journal-title":"J. Global Optim."},{"issue":"3","key":"1228_CR89","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1007\/s10898-017-0601-2","volume":"70","author":"KA Khan","year":"2018","unstructured":"Khan, K.A., Wilhelm, M., Stuber, M.D., Cao, H., Watson, H.A.J., Barton, P.I.: Corrections to: Differentiable McCormick relaxations. J. Global Optim. 70(3), 705\u2013706 (2018). https:\/\/doi.org\/10.1007\/s10898-017-0601-2","journal-title":"J. Global Optim."},{"issue":"2","key":"1228_CR90","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1007\/s101070100263","volume":"91","author":"ED Dolan","year":"2002","unstructured":"Dolan, E.D., Mor\u00e9, J.J.: Benchmarking optimization software with performance profiles. Math. Program. 91(2), 201\u2013213 (2002). https:\/\/doi.org\/10.1007\/s101070100263","journal-title":"Math. Program."},{"issue":"1","key":"1228_CR91","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1137\/141000671","volume":"59","author":"J Bezanson","year":"2017","unstructured":"Bezanson, J., Edelman, A., Karpinski, S., Shah, V.B.: Julia: A fresh approach to numerical computing. SIAM Rev. 59(1), 65\u201398 (2017). https:\/\/doi.org\/10.1137\/141000671","journal-title":"SIAM Rev."},{"key":"1228_CR92","doi-asserted-by":"publisher","unstructured":"Sanders, D.P., Benet, L., lucaferranti, Agarwal, K., Richard, B., Grawitter, J., Gupta, E., Herbst, M.F., Forets, M., yashrajgupta, Hanson, E., van Dyk, B., Rackauckas, C., Vasani, R., Miclu\u0163a-C\u00e2mpeanu, S., Olver, S., Koolen, T., Wormell, C., V\u00e1zquez, F.A., TagBot, J., O\u2019Bryant, K., Carlsson, K., Piibeleht, M., Reno, Deits, R., Holy, T., Kaluba, M., matsueushi: JuliaIntervals\/IntervalArithmetic.jl: V0.18.2. https:\/\/doi.org\/10.5281\/zenodo.4739394","DOI":"10.5281\/zenodo.4739394"},{"key":"1228_CR93","unstructured":"Fedorov, G., Nguyen, K.T., Harrison, P., Singh, A.: Intel Math Kernel Library 2019 Update 2 Release Notes. (2019). https:\/\/software.intel.com\/en-us\/mkl"},{"key":"1228_CR94","doi-asserted-by":"publisher","unstructured":"Anderson, E., Bai, Z., Bischof, C., Blackford, L.S., Demmel, J., Dongarra, J., Croz, J.D., Greenbaum, A., Hammarling, S., McKenney, A., Sorensen, D.: LAPACK Users\u2019 Guide. Society for Industrial and Applied Mathematics, Philadelphia (1999). https:\/\/doi.org\/10.1137\/1.9780898719604","DOI":"10.1137\/1.9780898719604"},{"key":"1228_CR95","doi-asserted-by":"publisher","unstructured":"Wang, E., Zhang, Q., Shen, B., Zhang, G., Lu, X., Wu, Q., Wang, Y.: Intel math kernel library. In: High-Performance Computing on the Intel\u00ae Xeon Phi\u2122, pp. 167\u2013188. Springer, New York (2014). https:\/\/doi.org\/10.1007\/978-3-319-06486-4_7","DOI":"10.1007\/978-3-319-06486-4_7"},{"issue":"2","key":"1228_CR96","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1145\/567806.567807","volume":"28","author":"LS Blackford","year":"2002","unstructured":"Blackford, L.S., Petitet, A., Pozo, R., Remington, K., Whaley, R.C., Demmel, J., Dongarra, J., Duff, I., Hammarling, S., Henry, G., Heroux, M.: An updated set of basic linear algebra subprograms (BLAS). ACM Trans. Math. Softw. 28(2), 135\u2013151 (2002). https:\/\/doi.org\/10.1145\/567806.567807","journal-title":"ACM Trans. Math. Softw."},{"issue":"3","key":"1228_CR97","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1080\/10556788.2017.1335312","volume":"33","author":"S Vigerske","year":"2018","unstructured":"Vigerske, S., Gleixner, A.: SCIP: global optimization of mixed-integer nonlinear programs in a branch-and-cut framework. Optim. Methods Softw. 33(3), 563\u2013593 (2018). https:\/\/doi.org\/10.1080\/10556788.2017.1335312","journal-title":"Optim. Methods Softw."},{"key":"1228_CR98","doi-asserted-by":"publisher","unstructured":"Grant, M., Boyd, S., Ye, Y.: In: Liberti, L., Maculan, N. (eds.) Disciplined convex programming, pp. 155\u2013210. Springer, Boston (2006). https:\/\/doi.org\/10.1007\/0-387-30528-9_7","DOI":"10.1007\/0-387-30528-9_7"},{"issue":"3","key":"1228_CR99","doi-asserted-by":"publisher","first-page":"383","DOI":"10.1007\/s12532-018-0138-5","volume":"10","author":"A Khajavirad","year":"2018","unstructured":"Khajavirad, A., Sahinidis, N.V.: A hybrid LP\/NLP paradigm for global optimization relaxations. Math. Program. Comput. 10(3), 383\u2013421 (2018). https:\/\/doi.org\/10.1007\/s12532-018-0138-5","journal-title":"Math. Program. Comput."}],"container-title":["Journal of Global Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10898-022-01228-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10898-022-01228-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10898-022-01228-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,25]],"date-time":"2023-02-25T05:09:48Z","timestamp":1677301788000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10898-022-01228-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,29]]},"references-count":99,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["1228"],"URL":"https:\/\/doi.org\/10.1007\/s10898-022-01228-x","relation":{},"ISSN":["0925-5001","1573-2916"],"issn-type":[{"value":"0925-5001","type":"print"},{"value":"1573-2916","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,29]]},"assertion":[{"value":"30 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 August 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}