{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T21:13:03Z","timestamp":1784063583563,"version":"3.55.0"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2018,4,26]],"date-time":"2018-04-26T00:00:00Z","timestamp":1524700800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s00521-018-3495-0","type":"journal-article","created":{"date-parts":[[2018,4,26]],"date-time":"2018-04-26T05:46:32Z","timestamp":1524721592000},"page":"6685-6698","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":25,"title":["An adaptive mechanism to achieve learning rate dynamically"],"prefix":"10.1007","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2918-618X","authenticated-orcid":false,"given":"Jinjing","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4818-8770","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhanbo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanbin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,4,26]]},"reference":[{"issue":"7553","key":"3495_CR1","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":"3495_CR2","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: International conference on neural information processing systems. Curran Associates Inc., pp 1097\u20131105"},{"key":"3495_CR3","unstructured":"Tompson J, Jain A, Lecun Y et al (2014) Joint training of a convolutional network and a graphical model for human pose estimation. Eprint Arxiv, pp 1799\u20131807"},{"issue":"8","key":"3495_CR4","doi-asserted-by":"publisher","first-page":"1915","DOI":"10.1109\/TPAMI.2012.231","volume":"35","author":"C Farabet","year":"2013","unstructured":"Farabet C, Couprie C, Najman L et al (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915\u20131929","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3495_CR5","unstructured":"Alex K, Ilya S, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: NIPS"},{"issue":"6","key":"3495_CR6","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MSP.2012.2205597","volume":"29","author":"G Hinton","year":"2012","unstructured":"Hinton G, Deng L, Yu D et al (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag 29(6):82\u201397","journal-title":"IEEE Signal Process Mag"},{"key":"3495_CR7","unstructured":"Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems, pp 3104\u20133112"},{"key":"3495_CR8","unstructured":"Bahdanau D, Cho K, Bengio Y (2014) Neural machine translation by jointly learning to align and translate. arXiv preprint \n                    arXiv:1409.0473"},{"issue":"2","key":"3495_CR9","doi-asserted-by":"publisher","first-page":"263","DOI":"10.1021\/ci500747n","volume":"55","author":"J Ma","year":"2015","unstructured":"Ma J, Sheridan RP, Liaw A et al (2015) Deep neural nets as a method for quantitative structure-activity relationships. J Chem Inf Model 55(2):263","journal-title":"J Chem Inf Model"},{"issue":"6218","key":"3495_CR10","doi-asserted-by":"publisher","first-page":"1254806","DOI":"10.1126\/science.1254806","volume":"347","author":"HY Xiong","year":"2015","unstructured":"Xiong HY, Alipanahi B, Lee LJ et al (2015) The human splicing code reveals new insights into the genetic determinants of disease. Science 347(6218):1254806","journal-title":"Science"},{"key":"3495_CR11","doi-asserted-by":"crossref","unstructured":"Khalil-Hani M, Liew SS, Bakhteri R (2015) An optimized second order stochastic learning algorithm for neural network training. In: International conference on neural information processing. Springer, pp 38\u201345","DOI":"10.1007\/978-3-319-26532-2_5"},{"key":"3495_CR12","unstructured":"Blundell C, Cornebise J, Kavukcuoglu K, Wierstra D (2015) Weight uncertainty in neural networks. In: Proceedings of the 32nd International Conference on Machine Learning, Computer science, vol 37, pp 1613\u20131622"},{"key":"3495_CR13","first-page":"1139","volume":"28","author":"I Sutskever","year":"2013","unstructured":"Sutskever I, Martens J, Dahl GE et al (2013) On the importance of initialization and momentum in deep learning. ICML (3) 28:1139\u20131147","journal-title":"ICML (3)"},{"key":"3495_CR14","unstructured":"Johnson, R, Tong Z (2013) Accelerating stochastic gradient descent using predictive variance reduction. In: Advances in neural information processing systems, pp 315\u2013323"},{"key":"3495_CR15","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization. arXiv preprint \n                    arXiv:1412.6980"},{"issue":"5786","key":"3495_CR16","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton GE, Salakhutdinov RR (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504","journal-title":"Science"},{"key":"3495_CR17","doi-asserted-by":"crossref","unstructured":"Deng L, Li J, Huang JT et al (2013) Recent advances in deep learning for speech research at Microsoft. In: IEEE international conference on acoustics, speech and signal processing. IEEE, pp 8604\u20138608","DOI":"10.1109\/ICASSP.2013.6639345"},{"key":"3495_CR18","unstructured":"Dauphin Y, Pascanu R, Gulcehre C, Cho K, Ganguli S, Bengio Y (2014). Identifying and attacking the saddle point problem in high-dimensional non-convex optimization. arXiv, 1C14"},{"issue":"3","key":"3495_CR19","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1214\/aoms\/1177729586","volume":"22","author":"H Robbins","year":"1951","unstructured":"Robbins H, Monro S (1951) A stochastic approximation method. Ann Math Stat 22(3):400\u2013407","journal-title":"Ann Math Stat"},{"key":"3495_CR20","doi-asserted-by":"crossref","unstructured":"Darken C, Chang J, Moody J (1992) Learning rate schedules for faster stochastic gradient search. In: Neural networks for signal processing II, proceedings of the 1992 IEEE workshop, (September), 1C11","DOI":"10.1109\/NNSP.1992.253713"},{"key":"3495_CR21","unstructured":"Sutton RS (1986) Two problems with backpropagation and other steepest-descent learning procedures for networks. In: Proceedings of 8th annual conference. Cognitive Science Society"},{"key":"3495_CR22","unstructured":"Bottou L (1991) Stochastic gradient learning in neural networks. In: Neuro-Nimes"},{"key":"3495_CR23","unstructured":"Zeiler MD (2012) ADADELTA: an adaptive learning rate method. \n                    arXiv:1212.5701"},{"key":"3495_CR24","unstructured":"Nesterov Y (1983) A method for unconstrained convex minimization problem with the rate of convergence o(1\/k2). Doklady ANSSSR (translated as Soviet. Math. Docl.), vol 269, pp 543\u2013547"},{"key":"3495_CR25","first-page":"8624","volume-title":"IEEE international conference on acoustics, speech and signal processing (ICASSP)","author":"Y Bengio","year":"2013","unstructured":"Bengio Y, Boulanger-Lewandowski N, Pascanu R (2013) Advances in optimizing recurrent networks. IEEE international conference on acoustics, speech and signal processing (ICASSP). IEEE, Vancouver, BC, Canada, pp 8624\u20138628"},{"issue":"1","key":"3495_CR26","doi-asserted-by":"publisher","first-page":"145C151","DOI":"10.1016\/S0893-6080(98)00116-6","volume":"12","author":"N Qian","year":"1999","unstructured":"Qian N (1999) On the momentum term in gradient descent learning algorithms. Neural Netw: The Official Journal of the International Neural Network Society 12(1):145C151","journal-title":"Neural Netw: The Official Journal of the International Neural Network Society"},{"key":"3495_CR27","first-page":"2121C2159","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 12:2121C2159","journal-title":"J Mach Learn Res"},{"key":"3495_CR28","unstructured":"Dean J, Corrado GS, Monga R, Chen K, Devin M, Le QV, Ng AY (2012) Large scale distributed deep networks. In: NIPS 2012: neural information processing systems, 1C11"},{"key":"3495_CR29","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning CD (2014) Glove: global vectors for word representation. In: Proceedings of the 2014 conference on empirical methods in natural language processing, pp 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"3495_CR30","first-page":"343","volume":"28","author":"T Schaul","year":"2012","unstructured":"Schaul T, Zhang S, Lecun Y (2012) No more pesky. Learn Rates 28:343\u2013351","journal-title":"Learn Rates"},{"key":"3495_CR31","unstructured":"Maas AL, Daly RE, Pham PT et al (2011) Learning word vectors for sentiment analysis. In: Proceedings of the 49th annual meeting of the association for computational linguistics: human language technologies-volume 1. Association for Computational Linguistics, pp 142\u2013150"},{"key":"3495_CR32","doi-asserted-by":"crossref","unstructured":"Nakov P, Ritter A, Rosenthal S, Sebastiani F, Stoyanov V (2011) Evaluation measures for the SemEval-2016 ask 4 sentiment analysis in Twitter. \n                    http:\/\/alt.qcri.org\/semeval2016\/task4\/","DOI":"10.18653\/v1\/S16-1001"},{"key":"3495_CR33","unstructured":"Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. Technical report, University of Toronto"},{"issue":"2","key":"3495_CR34","doi-asserted-by":"publisher","first-page":"303","DOI":"10.1007\/s11263-009-0275-4","volume":"88","author":"M Everingham","year":"2010","unstructured":"Everingham M, Gool LV, Williams CKI et al (2010) The pascal, visual object classes (VOC) challenge. Int J Comput Vis 88(2):303\u2013338","journal-title":"Int J Comput Vis"},{"issue":"8","key":"3495_CR35","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":"3495_CR36","unstructured":"Guo J (2013) Backpropagation through time. Unpubl. ms., Harbin Institute of Technology"},{"issue":"2","key":"3495_CR37","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1109\/TII.2016.2601521","volume":"13","author":"H Zhang","year":"2017","unstructured":"Zhang H, Li J, Ji Y, Yue H (2017) Understanding subtitles by character-level sequence-to-sequence learning. IEEE Trans Ind Inf 13(2):616\u2013624","journal-title":"IEEE Trans Ind Inf"},{"key":"3495_CR38","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/978-3-319-55753-3_25","volume-title":"International conference on database systems for advanced applications","author":"F Hu","year":"2017","unstructured":"Hu F, Xu X, Wang J, Yang Z, Li L (2017) Memory-enhanced latent semantic model: short text understanding for sentiment analysis. International conference on database systems for advanced applications. Springer, Cham, pp 393\u2013407"},{"key":"3495_CR39","unstructured":"Steijvers M, Grunwald P (1996) A recurrent network that performs a context-sensitive prediction task. In: Conference of the cognitive science"},{"key":"3495_CR40","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15:1929\u201358","journal-title":"J Mach Learn Res"},{"key":"3495_CR41","unstructured":"Wang S, Manning CD (2013) Fast dropout training. In: Proceedings of the 30th international conference on machine learning, pp 118\u2013126. ACM"},{"key":"3495_CR42","unstructured":"Wang S, Manning C (2013) Fast dropout training. In: Proceedings of the 30th international conference on machine learning (ICML-13), pp 118\u2013126"},{"key":"3495_CR43","unstructured":"Babaeizadeh M, Smaragdis P, Campbell RH (2016) NoiseOut: a simple way to prune neural networks. In: Emdnn Nips workshops. \n                    arXiv:1611.06211"},{"key":"3495_CR44","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. International conference on learning representations, computer science, pp 1150\u20131210"},{"key":"3495_CR45","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":"3495_CR46","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"3495_CR47","doi-asserted-by":"publisher","first-page":"211C252","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 115:211C252","journal-title":"Int J Comput Vis"},{"key":"3495_CR48","doi-asserted-by":"publisher","first-page":"2278C2323","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 86:2278C2323","journal-title":"Proc IEEE"},{"issue":"4","key":"3495_CR49","doi-asserted-by":"publisher","first-page":"1006","DOI":"10.1109\/TFUZZ.2016.2574915","volume":"25","author":"Y Deng","year":"2017","unstructured":"Deng Y, Ren Z, Kong Y et al (2017) A hierarchical fused fuzzy deep neural network for data classification. IEEE Trans Fuzzy Syst 25(4):1006\u20131012","journal-title":"IEEE Trans Fuzzy Syst"},{"issue":"3","key":"3495_CR50","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1109\/TNNLS.2016.2522401","volume":"28","author":"D Yue","year":"2017","unstructured":"Yue D, Feng B, Kong Y, Ren Z, Dai Q (2017) Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans Neural Netw Learn Syst 28(3):653\u2013664","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"12","key":"3495_CR51","doi-asserted-by":"publisher","first-page":"2537","DOI":"10.1109\/TNNLS.2015.2496281","volume":"27","author":"H Zhang","year":"2016","unstructured":"Zhang H, Chow TWS, Wu QMJ (2016) Organizing books and authors by multilayer SOM. IEEE Trans Neural Netw Learn Syst 27(12):2537","journal-title":"IEEE Trans Neural Netw Learn Syst"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3495-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-018-3495-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-018-3495-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,10,20]],"date-time":"2019-10-20T16:47:33Z","timestamp":1571590053000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-018-3495-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,4,26]]},"references-count":51,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["3495"],"URL":"https:\/\/doi.org\/10.1007\/s00521-018-3495-0","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,4,26]]},"assertion":[{"value":"4 August 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 April 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 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 conflict of interest","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}