{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:20:28Z","timestamp":1740108028700,"version":"3.37.3"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2018,9,19]],"date-time":"2018-09-19T00:00:00Z","timestamp":1537315200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100010661","name":"Horizon 2020 Framework Programme","doi-asserted-by":"publisher","award":["731667"],"award-info":[{"award-number":["731667"]}],"id":[{"id":"10.13039\/100010661","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2019,6]]},"DOI":"10.1007\/s00521-018-3712-x","type":"journal-article","created":{"date-parts":[[2018,9,19]],"date-time":"2018-09-19T10:44:23Z","timestamp":1537353863000},"page":"1733-1745","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Long-term temporal averaging for stochastic optimization of deep neural networks"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1177-9139","authenticated-orcid":false,"given":"Nikolaos","family":"Passalis","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anastasios","family":"Tefas","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,9,19]]},"reference":[{"issue":"3","key":"3712_CR1","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252. https:\/\/doi.org\/10.1007\/s11263-015-0816-y","journal-title":"Int J Comput Vis"},{"key":"3712_CR2","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D, Szegedy C, Reed S, Fu CY, Berg AC (2016) SSD: single shot multibox detector. In: Proceedings of the European conference on computer vision, pp 21\u201337 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"3712_CR3","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A (2016) You only look once: unified, real-time object detection. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 779\u2013788","DOI":"10.1109\/CVPR.2016.91"},{"key":"3712_CR4","unstructured":"Van den Oord A, Dieleman S, Zen H, Simonyan K, Vinyals O, Graves A, Kalchbrenner N, Senior A, Kavukcuoglu K (2016) Wavenet: a generative model for raw audio. In: 9th ISCA speech synthesis workshop, pp 125\u2013125"},{"issue":"7553","key":"3712_CR5","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":"3712_CR6","doi-asserted-by":"crossref","unstructured":"Passalis N, Tefas A (2017) Concept detection and face pose estimation using lightweight convolutional neural networks for steering drone video shooting. In: Proceedings of the European signal processing conference, pp 71\u201375","DOI":"10.23919\/EUSIPCO.2017.8081171"},{"key":"3712_CR7","doi-asserted-by":"crossref","unstructured":"Smolyanskiy N, Kamenev A, Smith J, Birchfield S (2017) Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness. arXiv preprint arXiv:1705.02550","DOI":"10.1109\/IROS.2017.8206285"},{"issue":"2","key":"3712_CR8","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1007\/s00521-015-2059-9","volume":"28","author":"R Arunkumar","year":"2017","unstructured":"Arunkumar R, Karthigaikumar P (2017) Multi-retinal disease classification by reduced deep learning features. Neural Comput Appl 28(2):329\u2013334","journal-title":"Neural Comput Appl"},{"key":"3712_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3158-6","author":"F Jiang","year":"2018","unstructured":"Jiang F, Grigorev A, Rho S, Tian Z, Fu Y, Jifara W, Adil K, Liu S (2018) Medical image semantic segmentation based on deep learning. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-017-3158-6","journal-title":"Neural Comput Appl"},{"key":"3712_CR10","unstructured":"Liu Y, Gadepalli K, Norouzi M, Dahl GE, Kohlberger T, Boyko A, Venugopalan S, Timofeev A, Nelson PQ, Corrado GS et al (2017) Detecting cancer metastases on gigapixel pathology images. arXiv preprint arXiv:1703.02442"},{"key":"3712_CR11","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3138-x","author":"X Wang","year":"2017","unstructured":"Wang X, Guo Y, Wang Y, Yu J (2017) Automatic breast tumor detection in ABVS images based on convolutional neural network and superpixel patterns. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-017-3138-x","journal-title":"Neural Comput Appl"},{"key":"3712_CR12","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3077-6","author":"D Yuxin","year":"2017","unstructured":"Yuxin D, Siyi Z (2017) Malware detection based on deep learning algorithm. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-017-3077-6","journal-title":"Neural Comput Appl"},{"issue":"2","key":"3712_CR13","doi-asserted-by":"publisher","first-page":"157","DOI":"10.1109\/72.279181","volume":"5","author":"Y Bengio","year":"1994","unstructured":"Bengio Y, Simard P, Frasconi P (1994) Learning long-term dependencies with gradient descent is difficult. IEEE Trans Neural Netw 5(2):157\u2013166","journal-title":"IEEE Trans Neural Netw"},{"key":"3712_CR14","unstructured":"Sutskever I, Martens J, Dahl G, Hinton G (2013) On the importance of initialization and momentum in deep learning. In: Proceedings of the international conference on machine learning, pp 1139\u20131147"},{"key":"3712_CR15","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3210-6","author":"A Farzad","year":"2017","unstructured":"Farzad A, Mashayekhi H, Hassanpour H (2017) A comparative performance analysis of different activation functions in LSTM networks for classification. Neural Comput Appl. https:\/\/doi.org\/10.1007\/s00521-017-3210-6","journal-title":"Neural Comput Appl"},{"key":"3712_CR16","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 international conference on computer vision, pp 1026\u20131034","DOI":"10.1109\/ICCV.2015.123"},{"key":"3712_CR17","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"3712_CR18","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, pp 448\u2013456"},{"key":"3712_CR19","unstructured":"Kingma D, Ba J (2015) Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980"},{"key":"3712_CR20","unstructured":"Srivastava RK, Greff K, Schmidhuber J (2015) Highway networks. arXiv preprint arXiv:1505.00387"},{"key":"3712_CR21","unstructured":"Moulines E, Bach FR (2011) Non-asymptotic analysis of stochastic approximation algorithms for machine learning. In: Proceedings of the advances in neural information processing systems, pp 451\u2013459 (2011)"},{"issue":"4","key":"3712_CR22","doi-asserted-by":"publisher","first-page":"838","DOI":"10.1137\/0330046","volume":"30","author":"BT Polyak","year":"1992","unstructured":"Polyak BT, Juditsky AB (1992) Acceleration of stochastic approximation by averaging. SIAM J Control Optim 30(4):838\u2013855","journal-title":"SIAM J Control Optim"},{"key":"3712_CR23","unstructured":"Ruppert D (1988) Efficient estimations from a slowly convergent Robbins\u2013Monro process. Technical report, Cornell University Operations Research and Industrial Engineering"},{"key":"3712_CR24","doi-asserted-by":"crossref","unstructured":"Passalis N, Tefas A (2017) Improving face pose estimation using long-term temporal averaging for stochastic optimization. In: Proceedings of the international conference on engineering applications of neural networks, pp 194\u2013204","DOI":"10.1007\/978-3-319-65172-9_17"},{"key":"3712_CR25","first-page":"2121","volume":"12","author":"J Duchi","year":"2011","unstructured":"Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121\u20132159","journal-title":"J Mach Learn Res"},{"key":"3712_CR26","unstructured":"Zeiler MD (2012) ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701"},{"key":"3712_CR27","doi-asserted-by":"crossref","unstructured":"Van Hasselt H, Guez A, Silver D (2016) Deep reinforcement learning with double Q-learning. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"3712_CR28","unstructured":"Anschel O, Baram N, Shimkin N (2017) Averaged-DQN: variance reduction and stabilization for deep reinforcement learning. In: Proceedings of the international conference on machine learning"},{"issue":"2004","key":"3712_CR29","first-page":"41","volume":"2","author":"S Haykin","year":"2004","unstructured":"Haykin S, Network N (2004) A comprehensive foundation. Neural Netw 2(2004):41","journal-title":"Neural Netw"},{"key":"3712_CR30","doi-asserted-by":"crossref","unstructured":"Passalis N, Tefas A, Pitas I (2018) Efficient camera control using 2D visual information for unmanned aerial vehicle-based cinematography. In: Proceedings of the IEEE international symposium on circuits and systems, pp 1\u20135","DOI":"10.1109\/ISCAS.2018.8351050"},{"key":"3712_CR31","doi-asserted-by":"crossref","unstructured":"Nousi P, Tefas A (2017) Discriminatively trained autoencoders for fast and accurate face recognition. In: Proceedings of the international conference on engineering applications of neural networks, pp 205\u2013215","DOI":"10.1007\/978-3-319-65172-9_18"},{"key":"3712_CR32","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-018-9235-y","author":"P Nousi","year":"2018","unstructured":"Nousi P, Tefas A (2018) Self-supervised autoencoders for clustering and classification. Evol Syst. https:\/\/doi.org\/10.1007\/s12530-018-9235-y","journal-title":"Evol Syst"},{"key":"3712_CR33","doi-asserted-by":"crossref","unstructured":"Mademlis I et al (2018) Challenges in autonomous UAV cinematography: an overview. In: Proceedings of the IEEE international conference on multimedia and expo","DOI":"10.1109\/ICME.2018.8486586"},{"key":"3712_CR34","unstructured":"Chollet F et al (2015) Keras. https:\/\/keras.io . Accessed 17 Sept 2018"},{"issue":"11","key":"3712_CR35","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324","journal-title":"Proc IEEE"},{"key":"3712_CR36","volume-title":"Neural networks and learning machines","author":"SS Haykin","year":"2009","unstructured":"Haykin SS, Haykin SS, Haykin SS, Haykin SS (2009) Neural networks and learning machines, vol 3. Pearson, Upper Saddle River"},{"issue":"1","key":"3712_CR37","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton GE, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929\u20131958","journal-title":"J Mach Learn Res"},{"key":"3712_CR38","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. Technical report, University of Toronto"},{"issue":"11","key":"3712_CR39","doi-asserted-by":"publisher","first-page":"1958","DOI":"10.1109\/TPAMI.2008.128","volume":"30","author":"A Torralba","year":"2008","unstructured":"Torralba A, Fergus R, Freeman WT (2008) 80 million tiny images: a large data set for nonparametric object and scene recognition. IEEE Trans Pattern Anal Mach Intell 30(11):1958\u20131970","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3712_CR40","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747"},{"key":"3712_CR41","unstructured":"Gourier N, Hall D, Crowley JL (2004) Estimating face orientation from robust detection of salient facial structures. In: FG NET workshop on visual observation of deictic gestures"},{"key":"3712_CR42","unstructured":"Chollet F et al (2015) Keras. https:\/\/github.com\/fchollet\/keras . Accessed 17 Sept 2018"},{"key":"3712_CR43","doi-asserted-by":"crossref","unstructured":"Koestinger M, Wohlhart P, Roth PM, Bischof H (2011) Annotated facial landmarks in the wild: a large-scale, real-world database for facial landmark localization. In: First IEEE international workshop on benchmarking facial image analysis technologies","DOI":"10.1109\/ICCVW.2011.6130513"},{"key":"3712_CR44","unstructured":"Maas AL, Daly RE, Pham PT, Huang D, Ng AY, Potts C (2011) Learning word vectors for sentiment analysis. In: Proceedings of the annual meeting of the Association for Computational Linguistics: human language technologies pp 142\u2013150"},{"issue":"8","key":"3712_CR45","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"3712_CR46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-04898-2_420","volume-title":"Nonparametric statistical inference","author":"JD Gibbons","year":"2011","unstructured":"Gibbons JD, Chakraborti S (2011) Nonparametric statistical inference. Springer, Berlin"},{"key":"3712_CR47","unstructured":"Jones E, Oliphant E, Peterson P et al (2001) SciPy: open source scientific tools for Python. http:\/\/www.scipy.org\/ . Accessed 31 July 2018"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3712-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-018-3712-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3712-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T22:39:10Z","timestamp":1662071950000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-018-3712-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9,19]]},"references-count":47,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2019,6]]}},"alternative-id":["3712"],"URL":"https:\/\/doi.org\/10.1007\/s00521-018-3712-x","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"type":"print","value":"0941-0643"},{"type":"electronic","value":"1433-3058"}],"subject":[],"published":{"date-parts":[[2018,9,19]]},"assertion":[{"value":"15 January 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors declare that they have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}]}}