{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T12:00:21Z","timestamp":1793016021750,"version":"4.5.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"30","license":[{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T00:00:00Z","timestamp":1722470400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100019457","name":"Key Digital Technologies Joint Undertaking","doi-asserted-by":"publisher","award":["101097300"],"award-info":[{"award-number":["101097300"]}],"id":[{"id":"10.13039\/100019457","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Alma Mater Studiorum - Universit\u00e0 di Bologna"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput &amp; Applic"],"published-print":{"date-parts":[[2024,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this work, we target the efficient implementation of spiking neural networks (SNNs) for low-power and low-latency applications. In particular, we propose a methodology for tuning SNN spiking activity with the objective of reducing computation cycles and energy consumption. We performed an analysis to devise key hyper-parameters, and then we show the results of tuning such parameters to obtain a low-latency and low-energy embedded LSNN (eLSNN) implementation. We demonstrate that it is possible to adapt the firing rate so that the samples belonging to the most frequent class are processed with less spikes. We implemented the eLSNN on a microcontroller-based sensor node and we evaluated its performance and energy consumption using a structural health monitoring application processing a stream of vibrations for damage detection (i.e. binary classification). We obtained a cycle count reduction of 25% and an energy reduction of 22% with respect to a baseline implementation. We also demonstrate that our methodology is applicable to a multi-class scenario, showing that we can reduce spiking activity between 68 and 85% at iso-accuracy.<\/jats:p>","DOI":"10.1007\/s00521-024-10191-5","type":"journal-article","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T17:02:33Z","timestamp":1722531753000},"page":"18897-18917","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Energy efficient and low-latency spiking neural networks on embedded microcontrollers through spiking activity tuning"],"prefix":"10.1007","volume":"36","author":[{"given":"Francesco","family":"Barchi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emanuele","family":"Parisi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luca","family":"Zanatta","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Bartolini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7323-759X","authenticated-orcid":false,"given":"Andrea","family":"Acquaviva","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"issue":"9","key":"10191_CR1","doi-asserted-by":"publisher","first-page":"1659","DOI":"10.1016\/S0893-6080(97)00011-7","volume":"10","author":"W Maass","year":"1997","unstructured":"Maass W (1997) Networks of spiking neurons: the third generation of neural network models. Neural Netw 10(9):1659\u20131671. https:\/\/doi.org\/10.1016\/S0893-6080(97)00011-7","journal-title":"Neural Netw"},{"key":"10191_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104362","volume":"104","author":"J Liu","year":"2021","unstructured":"Liu J, Lu H, Luo Y, Yang S (2021) Spiking neural network-based multi-task autonomous learning for mobile robots. Eng Appl Artif Intell 104:104362. https:\/\/doi.org\/10.1016\/j.engappai.2021.104362","journal-title":"Eng Appl Artif Intell"},{"key":"10191_CR3","doi-asserted-by":"publisher","DOI":"10.3390\/fi13080219","author":"F Barchi","year":"2021","unstructured":"Barchi F, Zanatta L, Parisi E, Burrello A, Brunelli D, Bartolini A, Acquaviva A (2021) Spiking neural network-based near-sensor computing for damage detection in structural health monitoring. Fut Internet. https:\/\/doi.org\/10.3390\/fi13080219","journal-title":"Fut Internet"},{"key":"10191_CR4","doi-asserted-by":"publisher","first-page":"118","DOI":"10.3389\/fnins.2011.00118","volume":"5","author":"G Indiveri","year":"2011","unstructured":"Indiveri G, Horiuchi T (2011) Frontiers in neuromorphic engineering. Front Neurosci 5:118. https:\/\/doi.org\/10.3389\/fnins.2011.00118","journal-title":"Front Neurosci"},{"issue":"7784","key":"10191_CR5","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","volume":"575","author":"K Roy","year":"2019","unstructured":"Roy K, Jaiswal A, Panda P (2019) Towards spike-based machine intelligence with neuromorphic computing. Nature 575(7784):607\u2013617. https:\/\/doi.org\/10.1038\/s41586-019-1677-2","journal-title":"Nature"},{"key":"10191_CR6","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/j.neunet.2019.09.005","volume":"121","author":"L Deng","year":"2020","unstructured":"Deng L, Wu Y, Hu X, Liang L, Ding Y, Li G, Zhao G, Li P, Xie Y (2020) Rethinking the performance comparison between snns and anns. Neural Netw 121:294\u2013307. https:\/\/doi.org\/10.1016\/j.neunet.2019.09.005","journal-title":"Neural Netw"},{"key":"10191_CR7","doi-asserted-by":"publisher","unstructured":"Lamba S, Lamba R (2019) Spiking neural networks vs convolutional neural networks for supervised learning. In: 2019 International Conference on Computing, Communication, and Intelligent Systems (ICCCIS), pp 15\u201319. https:\/\/doi.org\/10.1109\/icccis48478.2019.8974507","DOI":"10.1109\/icccis48478.2019.8974507"},{"key":"10191_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/jetcas.2015.2433552","author":"X Wu","year":"2015","unstructured":"Wu X, Saxena V, Zhu K (2015) Homogeneous spiking neuromorphic system for real-world pattern recognition. IEEE J Emerg Select Top Circ Syst. https:\/\/doi.org\/10.1109\/jetcas.2015.2433552","journal-title":"IEEE J Emerg Select Top Circ Syst"},{"issue":"4","key":"10191_CR9","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1109\/jetcas.2019.2952642","volume":"9","author":"Y Sakai","year":"2019","unstructured":"Sakai Y, Pedroni BU, Joshi S, Tanabe S, Akinin A, Cauwenberghs G (2019) Dropout and dropconnect for reliable neuromorphic inference under communication constraints in network connectivity. IEEE J Emerg Select Top Circ Syst 9(4):658\u2013667. https:\/\/doi.org\/10.1109\/jetcas.2019.2952642","journal-title":"IEEE J Emerg Select Top Circ Syst"},{"issue":"9","key":"10191_CR10","doi-asserted-by":"publisher","first-page":"7017","DOI":"10.1007\/s00521-022-07910-1","volume":"35","author":"A Stanojevic","year":"2023","unstructured":"Stanojevic A, Cherubini G, Wo\u017aniak S, Eleftheriou E (2023) Time-encoded multiplication-free spiking neural networks: application to data classification tasks. Neural Comput Appl 35(9):7017\u20137033. https:\/\/doi.org\/10.1007\/s00521-022-07910-1","journal-title":"Neural Comput Appl"},{"key":"10191_CR11","doi-asserted-by":"publisher","unstructured":"Madrenas J, Zapata M, Fern\u00e1ndez D, S\u00e1nchez-Chiva JM, Valle J, Mata-Hern\u00e1ndez D, Oltra JA, Cosp-Vilella J, Sato S (2020) Towards efficient and adaptive cyber physical spiking neural integrated systems. In: 2020 27th IEEE International Conference on Electronics, Circuits and Systems (ICECS), pp 1\u20134. https:\/\/doi.org\/10.1109\/icecs49266.2020.9294982","DOI":"10.1109\/icecs49266.2020.9294982"},{"key":"10191_CR12","doi-asserted-by":"publisher","unstructured":"Zhao J, Risi N, Monforte M, Bartolozzi C, Indiveri G, Donati E (2020) Closed-loop spiking control on a neuromorphic processor implemented on the icub. IEEE J Emerg Select Top Circ Syst 10(4):546\u2013556 https:\/\/doi.org\/10.1109\/jetcas.2020.3040390. arXiv:2009.09081 [cs.ET]","DOI":"10.1109\/jetcas.2020.3040390"},{"key":"10191_CR13","doi-asserted-by":"publisher","unstructured":"Eshraghian JK, Ward M, Neftci E, Wang X, Lenz G, Dwivedi G, Bennamoun M, Jeong DS, Lu WD (2023) Training spiking neural networks using lessons from deep learning. Proceedings of the IEEE 111(9):1016\u20131054. https:\/\/doi.org\/10.1109\/JPROC.2023.3308088","DOI":"10.1109\/JPROC.2023.3308088"},{"key":"10191_CR14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-020-17236-y","volume":"11","author":"G Bellec","year":"2020","unstructured":"Bellec G, Scherr F, Subramoney A, Hajek E, Salaj D, Legenstein R, Maass W (2020) A solution to the learning dilemma for recurrent networks of spiking neurons. Nat Commun 11:1\u201315","journal-title":"Nat Commun"},{"key":"10191_CR15","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00508","author":"JH Lee","year":"2016","unstructured":"Lee JH, Delbruck T, Pfeiffer M (2016) Training deep spiking neural networks using backpropagation. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2016.00508","journal-title":"Front Neurosci"},{"key":"10191_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-023-08650-6","author":"D Valencia","year":"2023","unstructured":"Valencia D, Alimohammad A (2023) A generalized hardware architecture for real-time spiking neural networks. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-023-08650-6","journal-title":"Neural Comput Appl"},{"key":"10191_CR17","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.773954","author":"Y Kim","year":"2021","unstructured":"Kim Y, Panda P (2021) Revisiting batch normalization for training low-latency deep spiking neural networks from scratch. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2021.773954","journal-title":"Front Neurosci"},{"key":"10191_CR18","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.629000","author":"S Hwang","year":"2021","unstructured":"Hwang S, Chang J, Oh M-H, Min KK, Jang T, Park K, Yu J, Lee J-H, Park B-G (2021) Low-latency spiking neural networks using pre-charged membrane potential and delayed evaluation. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2021.629000","journal-title":"Front Neurosci"},{"issue":"1","key":"10191_CR19","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1109\/TBCAS.2017.2759700","volume":"12","author":"S Moradi","year":"2017","unstructured":"Moradi S, Qiao N, Stefanini F, Indiveri G (2017) A scalable multicore architecture with heterogeneous memory structures for dynamic neuromorphic asynchronous processors (dynaps). IEEE Trans Biomed Circuits Syst 12(1):106\u2013122","journal-title":"IEEE Trans Biomed Circuits Syst"},{"key":"10191_CR20","doi-asserted-by":"crossref","unstructured":"Schemmel J, Fieres J, Meier K (2008) Wafer-scale integration of analog neural networks. In: 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence), pp 431\u2013438. Ieee","DOI":"10.1109\/IJCNN.2008.4633828"},{"issue":"5","key":"10191_CR21","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/JPROC.2014.2313565","volume":"102","author":"BV Benjamin","year":"2014","unstructured":"Benjamin BV, Gao P, McQuinn E, Choudhary S, Chandrasekaran AR, Bussat J, Alvarez-Icaza R, Arthur JV, Merolla PA, Boahen K (2014) Neurogrid: a mixed-analog-digital multichip system for large-scale neural simulations. Proc IEEE 102(5):699\u2013716","journal-title":"Proc IEEE"},{"issue":"1","key":"10191_CR22","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","volume":"38","author":"M Davies","year":"2018","unstructured":"Davies M, Srinivasa N, Lin T-H, Chinya G, Cao Y, Choday SH, Dimou G, Joshi P, Imam N, Jain S et al (2018) Loihi: a neuromorphic manycore processor with on-chip learning. IEEE Micro 38(1):82\u201399","journal-title":"IEEE Micro"},{"issue":"05","key":"10191_CR23","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1109\/mc.2019.2903009","volume":"52","author":"MV DeBole","year":"2019","unstructured":"...DeBole MV, Taba B, Amir A, Akopyan F, Andreopoulos A, Risk WP, Kusnitz J, Otero CO, Nayak TK, Appuswamy R, Carlson PJ, Cassidy AS, Datta P, Esser SK, Garreau GJ, Holland KL, Lekuch S, Mastro M, McKinstry J, Nolfo C, Paulovicks B, Sawada J, Schleupen K, Shaw BG, Klamo JL, Flickner MD, Arthur JV, Modha DS (2019) Truenorth: accelerating from zero to 64 million neurons in 10 years. Computer 52(05):20\u201329. https:\/\/doi.org\/10.1109\/mc.2019.2903009","journal-title":"Computer"},{"key":"10191_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.08.001","author":"W He","year":"2020","unstructured":"He W, Wu Y, Deng L, Li G, Wang H, Tian Y, Ding W, Wang W, Xie Y (2020) Comparing snns and rnns on neuromorphic vision datasets: similarities and differences. Neural Netw. https:\/\/doi.org\/10.1016\/j.neunet.2020.08.001","journal-title":"Neural Netw"},{"key":"10191_CR25","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.815258","author":"G Datta","year":"2022","unstructured":"Datta G, Kundu S, Jaiswal AR, Beerel PA (2022) Ace-snn: algorithm-hardware co-design of energy-efficient & low-latency deep spiking neural networks for 3d image recognition. Front Neurosci. https:\/\/doi.org\/10.3389\/fnins.2022.815258","journal-title":"Front Neurosci"},{"key":"10191_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104362","volume":"104","author":"J Liu","year":"2021","unstructured":"Liu J, Lu H, Luo Y, Yang S (2021) Spiking neural network-based multi-task autonomous learning for mobile robots. Eng Appl Artif Intell 104:104362. https:\/\/doi.org\/10.1016\/j.engappai.2021.104362","journal-title":"Eng Appl Artif Intell"},{"issue":"6","key":"10191_CR27","doi-asserted-by":"publisher","first-page":"4433","DOI":"10.1109\/JIOT.2020.3027102","volume":"8","author":"A Burrello","year":"2020","unstructured":"Burrello A, Marchioni A, Brunelli D, Benatti S, Mangia M, Benini L (2020) Embedded streaming principal components analysis for network load reduction in structural health monitoring. IEEE Internet Things J  8(6):4433\u20134447. https:\/\/doi.org\/10.1109\/JIOT.2020.3027102","journal-title":"IEEE Internet Things J."},{"key":"10191_CR28","doi-asserted-by":"publisher","DOI":"10.3390\/s20185126","author":"L Pang","year":"2020","unstructured":"Pang L, Liu J, Harkin J, Martin G, McElholm M, Javed A, McDaid L (2020) Case study-spiking neural network hardware system for structural health monitoring. Sensors. https:\/\/doi.org\/10.3390\/s20185126","journal-title":"Sensors"},{"key":"10191_CR29","volume-title":"MNIST handwritten digit database","author":"Y LeCun","year":"2010","unstructured":"LeCun Y, Cortes C, Burges C (2010) MNIST handwritten digit database. Florham Park, NJ, USA"},{"issue":"11","key":"10191_CR30","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1038\/81426","volume":"3","author":"M H\u00e4usser","year":"2000","unstructured":"H\u00e4usser M (2000) The hodgkin-huxley theory of the action potential. Nat Neurosci 3(11):1165\u20131165. https:\/\/doi.org\/10.1038\/81426","journal-title":"Nat Neurosci"},{"issue":"6","key":"10191_CR31","doi-asserted-by":"publisher","first-page":"1569","DOI":"10.1109\/tnn.2003.820440","volume":"14","author":"EM Izhikevich","year":"2003","unstructured":"Izhikevich EM (2003) Simple model of spiking neurons. IEEE Trans Neural Netw 14(6):1569\u20131572. https:\/\/doi.org\/10.1109\/tnn.2003.820440","journal-title":"IEEE Trans Neural Netw"},{"issue":"1","key":"10191_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00422-006-0068-6","volume":"95","author":"AN Burkitt","year":"2006","unstructured":"Burkitt AN (2006) A review of the integrate-and-fire neuron model: I. homogeneous synaptic input. Biol Cybern 95(1):1\u201319. https:\/\/doi.org\/10.1007\/s00422-006-0068-6","journal-title":"Biol Cybern"},{"issue":"10","key":"10191_CR33","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","volume":"78","author":"PJ Werbos","year":"1990","unstructured":"Werbos PJ (1990) Backpropagation through time: what it does and how to do it. Proc IEEE 78(10):1550\u20131560","journal-title":"Proc IEEE"},{"key":"10191_CR34","doi-asserted-by":"publisher","unstructured":"Chowdhury SS, Rathi N, Roy K (2021) One timestep is all you need: training spiking neural networks with ultra low latency. https:\/\/doi.org\/10.48550\/arXiv.2110.0592","DOI":"10.48550\/arXiv.2110.0592"},{"key":"10191_CR35","doi-asserted-by":"crossref","unstructured":"Datta G, Beerel PA (2022) Can deep neural networks be converted to ultra low-latency spiking neural networks? In: Proceedings of the 2022 Conference & Exhibition on Design, Automation & Test in Europe. Date \u201922, pp 718\u2013723. European Design and Automation Association, Leuven, BEL","DOI":"10.23919\/DATE54114.2022.9774704"},{"key":"10191_CR36","doi-asserted-by":"publisher","unstructured":"Datta G, Liu Z, Beerel PA (2022) Hoyer regularizer is all you need for ultra low-latency spiking neural networks. https:\/\/doi.org\/10.48550\/arXiv.2212.10170","DOI":"10.48550\/arXiv.2212.10170"},{"key":"10191_CR37","doi-asserted-by":"crossref","unstructured":"Li C, Jones EG, Furber S (2023) Unleashing the potential of spiking neural networks with dynamic confidence. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 13350\u201313360","DOI":"10.1109\/ICCV51070.2023.01228"},{"issue":"1","key":"10191_CR38","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1609\/aaai.v36i1.19874","volume":"36","author":"T Bu","year":"2022","unstructured":"Bu T, Ding J, Yu Z, Huang T (2022) Optimized potential initialization for low-latency spiking neural networks.  AAAI Conf Artif Intell 36(1):11\u201320. https:\/\/doi.org\/10.1609\/aaai.v36i1.19874","journal-title":"AAAI Conf Artif Intell"},{"key":"10191_CR39","unstructured":"Hao Z, Ding J, Bu T, Huang T, Yu Z (2023) Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes. ICLR 2023"},{"key":"10191_CR40","doi-asserted-by":"publisher","unstructured":"Meng Q, Xiao M, Yan S, Wang Y, Lin Z, Luo Z (2022) Training high-performance low-latency spiking neural networks by differentiation on spike representation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp 12434\u201312443. IEEE Computer Society, Los Alamitos, CA, USA. https:\/\/doi.org\/10.1109\/cvpr52688.2022.01212 . https:\/\/doi.ieeecomputersociety.org\/10.1109\/CVPR52688.2022.01212","DOI":"10.1109\/cvpr52688.2022.01212"},{"issue":"6","key":"10191_CR41","doi-asserted-by":"publisher","first-page":"3174","DOI":"10.1109\/tnnls.2021.3111897","volume":"34","author":"N Rathi","year":"2023","unstructured":"Rathi N, Roy K (2023) Diet-snn: a low-latency spiking neural network with direct input encoding and leakage and threshold optimization. IEEE Transs Neural Netw Learn Syst 34(6):3174\u20133182. https:\/\/doi.org\/10.1109\/tnnls.2021.3111897","journal-title":"IEEE Transs Neural Netw Learn Syst"},{"key":"10191_CR42","unstructured":"Li Y, Geller T, Kim Y, Panda P (2024) Seenn: towards temporal spiking early exit neural networks. In: Proceedings of the 37th International Conference on Neural Information Processing Systems (NIPS '23). Curran Associates Inc., Red Hook, NY, USA, Article 2764, 63327\u201363342"},{"key":"10191_CR43","doi-asserted-by":"crossref","unstructured":"Ding Y, Zuo L, Jing M, He P, Xiao Y (2024) Shrinking your timestep: towards low-latency neuromorphic object recognition with spiking neural network. arXiv preprint arXiv:2401.01912","DOI":"10.1609\/aaai.v38i10.29066"},{"key":"10191_CR44","doi-asserted-by":"crossref","unstructured":"Chowdhury SS, Rathi N, Roy K (2022) Towards ultra low latency spiking neural networks for vision and sequential tasks using temporal pruning. In: Avidan S, Brostow G, Ciss\u00e9 M, Farinella GM, Hassner T (eds) Computer Vision - ECCV 2022. Springer, Cham, pp 709\u2013726","DOI":"10.1007\/978-3-031-20083-0_42"},{"key":"10191_CR45","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126885","volume":"562","author":"L Zanatta","year":"2023","unstructured":"Zanatta L, Di Mauro A, Barchi F, Bartolini A, Benini L, Acquaviva A (2023) Directly-trained spiking neural networks for deep reinforcement learning: energy efficient implementation of event-based obstacle avoidance on a neuromorphic accelerator. Neurocomputing 562:126885","journal-title":"Neurocomputing"},{"key":"10191_CR46","doi-asserted-by":"crossref","unstructured":"Di\u00a0Mauro A, Prasad AS, Huang Z, Spallanzani M, Conti F, Benini L (2022) Sne: an energy-proportional digital accelerator for sparse event-based convolutions. In: 2022 Design, Automation & Test in Europe Conference & Exhibition (DATE), pp 825\u2013830. IEEE","DOI":"10.23919\/DATE54114.2022.9774552"},{"issue":"11","key":"10191_CR47","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10191-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00521-024-10191-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-024-10191-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:44:22Z","timestamp":1726764262000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00521-024-10191-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,1]]},"references-count":47,"journal-issue":{"issue":"30","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["10191"],"URL":"https:\/\/doi.org\/10.1007\/s00521-024-10191-5","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,1]]},"assertion":[{"value":"15 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 July 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2024","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 of this paper have declared that they do not have any conflict of interest to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}