{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T20:57:05Z","timestamp":1778101025814,"version":"3.51.4"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"24","license":[{"start":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T00:00:00Z","timestamp":1659052800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T00:00:00Z","timestamp":1659052800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2022,12]]},"DOI":"10.1007\/s00521-022-07625-3","type":"journal-article","created":{"date-parts":[[2022,7,29]],"date-time":"2022-07-29T16:49:18Z","timestamp":1659113358000},"page":"21729-21740","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["P\u2009+\u2009FELU: Flexible and trainable fast exponential linear unit for deep learning architectures"],"prefix":"10.1007","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3752-7354","authenticated-orcid":false,"given":"Kemal","family":"Adem","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,7,29]]},"reference":[{"key":"7625_CR1","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1016\/j.eswa.2018.07.053","volume":"114","author":"K Adem","year":"2018","unstructured":"Adem K (2018) Exudate detection for diabetic retinopathy with circular Hough transformation and convolutional neural networks. Expert Syst Appl 114:289\u2013295","journal-title":"Expert Syst Appl"},{"issue":"6","key":"7625_CR2","doi-asserted-by":"publisher","first-page":"4220","DOI":"10.3906\/elk-1903-112","volume":"27","author":"K Adem","year":"2019","unstructured":"Adem K, K\u00f6zkurt C (2019) Defect detection of seals in multilayer aseptic packages using deep learning. Turk J Electr Eng Comput Sci 27(6):4220\u20134230","journal-title":"Turk J Electr Eng Comput Sci"},{"key":"7625_CR3","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.eswa.2018.11.042","volume":"120","author":"VS Bawa","year":"2019","unstructured":"Bawa VS, Kumar V (2019) Linearized sigmoidal activation: A novel activation function with tractable non-linear characteristics to boost representation capability. Expert Syst Appl 120:346\u2013356","journal-title":"Expert Syst Appl"},{"key":"7625_CR4","unstructured":"Clevert, D. A., Unterthiner, T., & Hochreiter, S. (2015). Fast and accurate deep network learning by exponential linear units (Elus).\u00a0"},{"issue":"1","key":"7625_CR5","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1109\/TCSS.2021.3102591","volume":"9","author":"H Gao","year":"2021","unstructured":"Gao H, Xu K, Cao M, Xiao J, Xu Q, Yin Y (2021) The deep features and attention mechanism-based method to dish healthcare under social IoT systems: an empirical study with a hand-deep local-global net. IEEE Transact Comput Soc Syst 9(1):336\u2013347","journal-title":"IEEE Transact Comput Soc Syst"},{"key":"7625_CR6","unstructured":"Glorot, X., & Bengio, Y. (2010, March). Understanding the difficulty of training deep feedforward neural networks. In\u00a0Proceedings of the thirteenth int conf on art intell stat JMLR Workshop and Conference Proceedings: 249\u2013256)"},{"key":"7625_CR7","first-page":"3006","volume-title":"An evaluation of parametric activation functions for deep learning","author":"LB Godfrey","year":"2019","unstructured":"Godfrey LB (2019) An evaluation of parametric activation functions for deep learning. In IEEE Int Conf Syst, Man Cybern (SMC) IEEE, pp 3006\u20133011"},{"key":"7625_CR8","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1016\/j.patrec.2018.09.006","volume":"116","author":"F Godin","year":"2018","unstructured":"Godin F, Degrave J, Dambre J, De Neve W (2018) Dual rectified linear units (DReLUs): A replacement for tanh activation functions in quasi-recurrent neural networks. Pattern Recogn Lett 116:8\u201314","journal-title":"Pattern Recogn Lett"},{"key":"7625_CR9","doi-asserted-by":"crossref","unstructured":"Gupta, S., & Dinesh, D. A. (2017). Resource usage prediction of cloud workloads using deep bidirectional long short term memory networks. In\u00a02017 IEEE international conference on advanced networks and telecommunications systems (ANTS): 1\u20136 IEEE.","DOI":"10.1109\/ANTS.2017.8384098"},{"key":"7625_CR10","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\u00a0Proceedings of the IEEE international conference on computer vision: 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"issue":"4","key":"7625_CR11","first-page":"117","volume":"50","author":"ZHAO Huizhen","year":"2018","unstructured":"Huizhen ZHAO, Fuxian L, Longyue L (2018) A novel softplus linear unit for deep CNN. J Harbin Inst Technol 50(4):117\u2013123","journal-title":"J Harbin Inst Technol"},{"key":"7625_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114805","volume":"174","author":"S Kili\u00e7arslan","year":"2021","unstructured":"Kili\u00e7arslan S, Celik M (2021) RSigELU: A nonlinear activation function for deep neural networks. Expert Syst Appl 174:114805","journal-title":"Expert Syst Appl"},{"key":"7625_CR13","unstructured":"Kingma, D. P., & Ba, J. (2014). Adam: A method for stochastic optimization.\u00a0arXiv preprint ."},{"issue":"8","key":"7625_CR14","doi-asserted-by":"publisher","first-page":"3385","DOI":"10.1007\/s00521-020-05182-1","volume":"33","author":"J Kise\u013e\u00e1k","year":"2021","unstructured":"Kise\u013e\u00e1k J, Lu Y, \u0160vihra J, Sz\u00e9pe P, Stehl\u00edk M (2021) \u201cSPOCU\u201d: scaled polynomial constant unit activation function. Neural Comput Appl 33(8):3385\u20133401","journal-title":"Neural Comput Appl"},{"issue":"7553","key":"7625_CR15","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"7625_CR16","unstructured":"LeCun, Y., Boser, B., Denker, J., Henderson, D., Howard, R., Hubbard, W., & Jackel, L. (1989). Handwritten digit recognition with a back-propagation network.\u00a0Advances in neural information processing systems 2"},{"key":"7625_CR17","unstructured":"Lee, J., Shridhar, K., Hayashi, H., Iwana, B. K., Kang, S., & Uchida, S. (2019). Probact: A probabilistic activation function for deep neural networks.\u00a0arXiv preprint \u00a05, 13"},{"key":"7625_CR18","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, Wu Q, Ming Y (2018) Improving deep neural network with multiple parametric exponential linear units. Neurocomputing 301:11\u201324","journal-title":"Neurocomputing"},{"issue":"23","key":"7625_CR19","doi-asserted-by":"publisher","first-page":"17351","DOI":"10.1007\/s00521-020-04867-x","volume":"32","author":"IE Livieris","year":"2020","unstructured":"Livieris IE, Pintelas E, Pintelas P (2020) A CNN\u2013LSTM model for gold price time-series forecasting. Neural Comput Appl 32(23):17351\u201317360","journal-title":"Neural Comput Appl"},{"key":"7625_CR20","unstructured":"Maas, A. L., Hannun, A. Y., & Ng, A. Y. (2013, June). Rectifier nonlinearities improve neural network acoustic models. In\u00a0Proc Icml 30(1): 3"},{"key":"7625_CR21","unstructured":"Nair, V., & Hinton, G. E. (2010, January). Rectified linear units improve restricted boltzmann machines. In Proceedings of the 27th international conference on machine learning\u00a0(Icml): 807\u2013814"},{"key":"7625_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.physa.2019.122537","volume":"535","author":"MM Ozguven","year":"2019","unstructured":"Ozguven MM, Adem K (2019) Automatic detection and classification of leaf spot disease in sugar beet using deep learning algorithms. Physica A 535:122537","journal-title":"Physica A"},{"key":"7625_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2021.104519","volume":"134","author":"I Pacal","year":"2021","unstructured":"Pacal I, Karaboga D (2021) A Robust Real-Time Deep Learning Based Automatic Polyp Detection System. Comput Biol Med 134:104519","journal-title":"Comput Biol Med"},{"key":"7625_CR24","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","journal-title":"Ieee Access"},{"key":"7625_CR25","unstructured":"Ramachandran, P., Zoph, B., & Le, Q. V. (2017). Searching for activation functions.\u00a0arXiv preprint ."},{"key":"7625_CR26","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition.\u00a0arXiv preprint ."},{"key":"7625_CR27","doi-asserted-by":"crossref","unstructured":"Trottier, L., Giguere, P., & Chaib-Draa, B. (2017, December). Parametric exponential linear unit for deep convolutional neural networks. In\u00a02017 16th IEEE International Conference on Machine Learning and Applications (ICMLA): 207\u2013214 IEEE","DOI":"10.1109\/ICMLA.2017.00038"},{"key":"7625_CR28","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.neucom.2019.07.017","volume":"363","author":"X Wang","year":"2019","unstructured":"Wang X, Qin Y, Wang Y, Xiang S, Chen H (2019) ReLTanh: An activation function with vanishing gradient resistance for SAE-based DNNs and its application to rotating machinery fault diagnosis. Neurocomputing 363:88\u201398","journal-title":"Neurocomputing"},{"issue":"5","key":"7625_CR29","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.3390\/app10051897","volume":"10","author":"Y Wang","year":"2020","unstructured":"Wang Y, Li Y, Song Y, Rong X (2020) The influence of the activation function in a convolution neural network model of facial expression recognition. Appl Sci 10(5):1897","journal-title":"Appl Sci"},{"issue":"1s","key":"7625_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3419842","volume":"17","author":"J Xiao","year":"2021","unstructured":"Xiao J, Xu H, Gao H, Bian M, Li Y (2021) A weakly supervised semantic segmentation network by aggregating seed cues: the multi-object proposal generation perspective. ACM Transact Multimidia Comput Communicat Appl 17(1s):1\u201319","journal-title":"ACM Transact Multimidia Comput Communicat Appl"},{"issue":"1","key":"7625_CR31","first-page":"58","volume":"40","author":"T Zhang","year":"2019","unstructured":"Zhang T, Yang J, Song WA, Song CF (2019) Research on improved activation function TReLU. J Chinese Comput Syst 40(1):58\u201363","journal-title":"J Chinese Comput Syst"},{"key":"7625_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114534","volume":"171","author":"Y Zhou","year":"2021","unstructured":"Zhou Y, Li D, Huo S, Kung SY (2021) Shape autotuning activation function. Expert Syst Appl 171:114534","journal-title":"Expert Syst Appl"},{"key":"7625_CR33","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","journal-title":"Neurocomputing"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07625-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-022-07625-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-022-07625-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,8]],"date-time":"2022-11-08T00:01:50Z","timestamp":1667865710000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-022-07625-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,29]]},"references-count":33,"journal-issue":{"issue":"24","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["7625"],"URL":"https:\/\/doi.org\/10.1007\/s00521-022-07625-3","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,7,29]]},"assertion":[{"value":"27 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 July 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 July 2022","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 that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}