{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T10:27:22Z","timestamp":1780050442129,"version":"3.53.1"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62076117"],"award-info":[{"award-number":["62076117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangxi Provincial Key Laboratory of Virtual Reality","award":["2024SSY03151"],"award-info":[{"award-number":["2024SSY03151"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1007\/s00521-024-10935-3","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T09:06:25Z","timestamp":1736931985000},"page":"6465-6478","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Constructing a smoothed Leaky ReLU using a linear combination of the smoothed ReLU and identity function"],"prefix":"10.1007","volume":"37","author":[{"given":"Meng","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2526-2181","authenticated-orcid":false,"given":"Weidong","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengxue","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"key":"10935_CR1","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1016\/j.neunet.2023.01.041","volume":"161","author":"AG Menezes","year":"2023","unstructured":"Menezes AG, de Moura G, Alves C et al (2023) Continual object detection: a review of definitions, strategies, and challenges. Neural Netw 161:476\u2013493. https:\/\/doi.org\/10.1016\/j.neunet.2023.01.041","journal-title":"Neural Netw"},{"issue":"6","key":"10935_CR2","doi-asserted-by":"publisher","first-page":"3205","DOI":"10.1109\/TNNLS.2022.3176493","volume":"34","author":"M Shi","year":"2023","unstructured":"Shi M, Shen J, Yi Q et al (2023) Lmffnet: a well-balanced lightweight network for fast and accurate semantic segmentation. IEEE Trans Neural Netw Learn Syst 34(6):3205\u20133219. https:\/\/doi.org\/10.1109\/TNNLS.2022.3176493","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10935_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2023.109513","volume":"139","author":"Q Wang","year":"2023","unstructured":"Wang Q, Zhong Y, Min W et al (2023) Dual similarity pre-training and domain difference encouragement learning for vehicle re-identification in the wild. Pattern Recogn 139:1\u201311. https:\/\/doi.org\/10.1016\/j.patcog.2023.109513","journal-title":"Pattern Recogn"},{"key":"10935_CR4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3269666","author":"D Gai","year":"2023","unstructured":"Gai D, Feng R, Min W et al (2023) Spatiotemporal learning transformer for video-based human pose estimation. IEEE Trans Circuits Syst Video Technol. https:\/\/doi.org\/10.1109\/TCSVT.2023.3269666","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"10935_CR5","unstructured":"Glorot X, Bengio Y (2010) Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the International Conference on Artificial Intelligence and Statistics, vol 9, pp 249\u2013256"},{"issue":"2","key":"10935_CR6","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s40745-020-00253-5","volume":"9","author":"Q Wang","year":"2022","unstructured":"Wang Q, Ma Y, Zhao K, Tian Y (2022) A comprehensive survey of loss functions in machine learning. Ann Data Sci 9(2):187\u2013212. https:\/\/doi.org\/10.1007\/s40745-020-00253-5","journal-title":"Ann Data Sci"},{"issue":"4","key":"10935_CR7","first-page":"841","volume":"8","author":"GC Cawley","year":"2007","unstructured":"Cawley GC, Talbot NL (2007) Preventing over-fitting during model selection via Bayesian regularisation of the hyper-parameters. J Mach Learn Res 8(4):841\u2013861","journal-title":"J Mach Learn Res"},{"key":"10935_CR8","unstructured":"Sutskever I, Martens J, Dahl G et al (2013) On the importance of initialization and momentum in deep learning. In: Proceedings of the International Conference on Machine Learning, pp 1139\u20131147"},{"key":"10935_CR9","unstructured":"Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: Proceedings of the International Conference on Machine Learning"},{"issue":"1","key":"10935_CR10","first-page":"163","volume":"2","author":"W Duch","year":"1999","unstructured":"Duch W, Jankowski N (1999) Survey of neural transfer functions. Neural Comput Surv 2(1):163\u2013212","journal-title":"Neural Comput Surv"},{"issue":"6789","key":"10935_CR11","doi-asserted-by":"publisher","first-page":"947","DOI":"10.1038\/35016072","volume":"405","author":"RHR Hahnloser","year":"2000","unstructured":"Hahnloser RHR, Sarpeshkar R, Mahowald MA et al (2000) Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405(6789):947\u2013951","journal-title":"Nature"},{"key":"10935_CR12","doi-asserted-by":"publisher","unstructured":"Jarrett K, Kavukcuoglu K, Ranzato M, LeCun Y (2009) What is the best multi-stage architecture for object recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 2146\u20132153. https:\/\/doi.org\/10.1109\/ICCV.2009.5459469","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"10935_CR13","unstructured":"Nair V, Hinton GE (2010) Rectified linear units improve restricted boltzmann machines. In: Proceedings of the International Conference on Machine Learning, pp 807\u2013814"},{"issue":"3","key":"10935_CR14","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"23","author":"H Robbins","year":"1951","unstructured":"Robbins H, Monro S (1951) A stochastic approximation method. Ann Math Stat 23(3):400\u2013407","journal-title":"Ann Math Stat"},{"issue":"3","key":"10935_CR15","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1214\/aoms\/1177729392","volume":"23","author":"J Kiefer","year":"1952","unstructured":"Kiefer J, Wolfowitz J (1952) Stochastic estimation of the maximum of a regression function. Ann Math Stat 23(3):462\u2013466","journal-title":"Ann Math Stat"},{"key":"10935_CR16","unstructured":"Maas AL, Hannun AY, Ng AY (2013) Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the International Conference on Machine Learning"},{"key":"10935_CR17","unstructured":"Clevert DA, Unterthiner T, Hochreiter S (2016) Fast and accurate deep network learning by exponential linear units (elus). In: Proceedings of the International Conference on Learning Representations"},{"key":"10935_CR18","unstructured":"Hendrycks D, Gimpel K (2016) Bridging Nonlinearities and Stochastic Regularizers with Gaussian Error Linear Units. arXiv:1606.08415"},{"key":"10935_CR19","unstructured":"Ramachandran P, Zoph B, Le QV (2018) Searching for activation functions. In: Proceedings of the International Conference on Learning Representations"},{"key":"10935_CR20","unstructured":"Molina A, Schramowski P, Kersting K (2020) Pad\u00e9 activation units: End-to-end learning of flexible activation functions in deep networks. In: Proceedings of the International Conference on Learning Representations"},{"key":"10935_CR21","unstructured":"Devlin J, Chang MW, Lee K, Toutanova K (2019) Bert: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp 4171\u20134186"},{"key":"10935_CR22","unstructured":"Brown T, Mann B, Ryder N et al (2020) Language models are few-shot learners. In: Proceedings of the International Conference on Neural Information Processing Systems, vol 33, pp 1877\u20131901"},{"key":"10935_CR23","unstructured":"Ouyang L, Wu J, Jiang X et al (2022) Training language models to follow instructions with human feedback. In: Proceedings of the International Conference on Neural Information Processing Systems, vol 35, pp 27730\u201327744"},{"key":"10935_CR24","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"10935_CR25","unstructured":"Xu B, Wang N, Chen T, Li M (2015) Empirical Evaluation of Rectified Activations in Convolutional Network. arXiv:1505.00853"},{"key":"10935_CR26","doi-asserted-by":"crossref","unstructured":"Duggal R, Gupta A (2017) P-telu: Parametric tan hyperbolic linear unit activation for deep neural networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 974\u2013978","DOI":"10.1109\/ICCVW.2017.119"},{"key":"10935_CR27","unstructured":"Klambauer G, Unterthiner T, Mayr A, Hochreiter S (2017) Self-normalizing neural networks. In: Proceedings of the International Conference on Neural Information Processing Systems, vol 30"},{"key":"10935_CR28","doi-asserted-by":"publisher","unstructured":"Trottier L, Giguere P, Chaib-draa B (2017) Parametric exponential linear unit for deep convolutional neural networks. In: Proceedings of the IEEE International Conference on Machine Learning and Applications, pp 207\u2013214. https:\/\/doi.org\/10.1109\/ICMLA.2017.00038","DOI":"10.1109\/ICMLA.2017.00038"},{"key":"10935_CR29","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1016\/j.neucom.2018.01.084","volume":"301","author":"Y Li","year":"2018","unstructured":"Li Y, Fan C, Li Y et al (2018) Improving deep neural network with multiple parametric exponential linear units. Neurocomputing 301:11\u201324. https:\/\/doi.org\/10.1016\/j.neucom.2018.01.084","journal-title":"Neurocomputing"},{"key":"10935_CR30","doi-asserted-by":"publisher","first-page":"151359","DOI":"10.1109\/ACCESS.2019.2948112","volume":"7","author":"Z Qiumei","year":"2019","unstructured":"Qiumei Z, Dan T, Fenghua W (2019) Improved convolutional neural network based on fast exponentially linear unit activation function. IEEE Access 7:151359\u2013151367. https:\/\/doi.org\/10.1109\/ACCESS.2019.2948112","journal-title":"IEEE Access"},{"key":"10935_CR31","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1016\/j.neucom.2020.03.051","volume":"406","author":"D Kim","year":"2020","unstructured":"Kim D, Kim J, Kim J (2020) Elastic exponential linear units for convolutional neural networks. Neurocomputing 406:253\u2013266. https:\/\/doi.org\/10.1016\/j.neucom.2020.03.051","journal-title":"Neurocomputing"},{"key":"10935_CR32","unstructured":"Hinton GE, Srivastava N, Krizhevsky A et al (2012) Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors. arXiv:1207.0580"},{"key":"10935_CR33","unstructured":"Krueger D, Maharaj T, Kramar J et al (2017) Zoneout: Regularizing rnns by randomly preserving hidden activations. In: Proceedings of the International Conference on Neural Information Processing Systems"},{"key":"10935_CR34","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 (2018) Sigmoid-weighted linear units for neural network function approximation in reinforcement learning. Neural Netw 107:3\u201311. https:\/\/doi.org\/10.1016\/j.neunet.2017.12.012","journal-title":"Neural Netw"},{"key":"10935_CR35","doi-asserted-by":"crossref","unstructured":"Howard A, Sandler M, Chu G et al (2019) Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 1314\u20131324","DOI":"10.1109\/ICCV.2019.00140"},{"key":"10935_CR36","doi-asserted-by":"publisher","first-page":"101633","DOI":"10.1109\/ACCESS.2019.2928442","volume":"7","author":"Y Ying","year":"2019","unstructured":"Ying Y, Su J, Shan P et al (2019) Rectified exponential units for convolutional neural networks. IEEE Access 7:101633\u2013101640. https:\/\/doi.org\/10.1109\/ACCESS.2019.2928442","journal-title":"IEEE Access"},{"key":"10935_CR37","unstructured":"Misra D (2019) Mish: A Self Regularized Non-Monotonic Neural Activation Function. arXiv:1908.08681"},{"key":"10935_CR38","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1016\/j.neucom.2021.06.067","volume":"458","author":"H Zhu","year":"2021","unstructured":"Zhu H, Zeng H, Liu J, Zhang X (2021) Logish: a new nonlinear nonmonotonic activation function for convolutional neural network. Neurocomputing 458:490\u2013499. https:\/\/doi.org\/10.1016\/j.neucom.2021.06.067","journal-title":"Neurocomputing"},{"key":"10935_CR39","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.neucom.2020.11.068","volume":"429","author":"M Zhu","year":"2021","unstructured":"Zhu M, Min W, Wang Q et al (2021) PFLU and FPFLU: Two novel non-monotonic activation functions in convolutional neural networks. Neurocomputing 429:110\u2013117. https:\/\/doi.org\/10.1016\/j.neucom.2020.11.068","journal-title":"Neurocomputing"},{"issue":"4","key":"10935_CR40","doi-asserted-by":"publisher","first-page":"550","DOI":"10.3390\/electronics11040540","volume":"11","author":"X Wang","year":"2022","unstructured":"Wang X, Ren H, Wang A (2022) Smish: a novel activation function for deep learning methods. Electronics 11(4):550. https:\/\/doi.org\/10.3390\/electronics11040540","journal-title":"Electronics"},{"key":"10935_CR41","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-09035-5","author":"M Kaytan","year":"2023","unstructured":"Kaytan M, Aydilek IB, Yeroglu C (2023) Gish: a novel activation function for image classification. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-023-09035-5","journal-title":"Neural Comput Appl"},{"key":"10935_CR42","doi-asserted-by":"publisher","unstructured":"Biswas K, Kumar S, Banerjee S, Kumar\u00a0Pandey A (2022) Sau: Smooth activation function using convolution with approximate identities. In: Proceedings of the European Conference on Computer Vision, pp 313\u2013329. https:\/\/doi.org\/10.1007\/978-3-031-19803-8_19","DOI":"10.1007\/978-3-031-19803-8_19"},{"key":"10935_CR43","doi-asserted-by":"crossref","unstructured":"Biswas K, Kumar S, Banerjee S, Kumar\u00a0Pandey A (2022) Smooth maximum unit: Smooth activation function for deep networks using smoothing maximum technique. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 784\u2013793","DOI":"10.1109\/CVPR52688.2022.00087"},{"issue":"4","key":"10935_CR44","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun Y, Boser B, Denker JS et al (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541\u2013551. https:\/\/doi.org\/10.1162\/neco.1989.1.4.541","journal-title":"Neural Comput"},{"key":"10935_CR45","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning, vol 37, pp 448\u2013456"},{"key":"10935_CR46","unstructured":"Tan M, Le Q (2019) Efficientnet: Rethinking model scaling for convolutional neural networks. In: Proceedings of the International Conference on Machine Learning, vol 97, pp 6105\u20136114"},{"key":"10935_CR47","doi-asserted-by":"crossref","unstructured":"Radosavovic I, Kosaraju RP, Girshick R et al (2020) Designing network design spaces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 10428\u201310436","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"10935_CR48","unstructured":"Krizhevsky A, Hinton GE (2009) Learning Multiple Layers of Features from Tiny Images. https:\/\/citeseerx.ist.psu.edu"},{"key":"10935_CR49","unstructured":"Paszke A, Gross S, Massa F et al (2019) Pytorch: An imperative style, high-performance deep learning library. In: Proceedings of the International Conference on Neural Information Processing Systems, pp 8026\u20138037"},{"key":"10935_CR50","unstructured":"Saxe AM, McClelland JL, Ganguli S (2013) Exact Solutions to the Nonlinear Dynamics of Learning in Deep Linear Neural Networks. arXiv:1312.6120"},{"key":"10935_CR51","unstructured":"Everingham M, Winn J (2011) The pascal visual object classes challenge 2012 (voc2012) development kit. Pattern Analysis, Statistical Modelling and Computational Learning 8"},{"key":"10935_CR52","doi-asserted-by":"crossref","unstructured":"Cordts M, Omran M, Ramos S et al (2016) The cityscapes dataset for semantic urban scene understanding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3213\u20133223","DOI":"10.1109\/CVPR.2016.350"},{"key":"10935_CR53","doi-asserted-by":"publisher","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Proceedings of the Medical Image Computing and Computer-Assisted Intervention, vol 9351, pp 234\u2013241. https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28","DOI":"10.1007\/978-3-319-24574-4_28"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10935-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10935-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10935-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,6]],"date-time":"2025-03-06T17:34:45Z","timestamp":1741282485000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10935-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,15]]},"references-count":53,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2025,3]]}},"alternative-id":["10935"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10935-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,15]]},"assertion":[{"value":"2 March 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 January 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}