{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,3]],"date-time":"2026-09-03T15:24:18Z","timestamp":1788449058405,"version":"build-2803163510"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2021,8,1]],"date-time":"2021-08-01T00:00:00Z","timestamp":1627776000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"General Research Fund from the Research Grant Council of Hong Kong SAR","award":["RGC\/HKBU12201318"],"award-info":[{"award-number":["RGC\/HKBU12201318"]}]},{"name":"General Research Fund from the Research Grant Council of Hong Kong SAR","award":["RGC\/HKBU12201619"],"award-info":[{"award-number":["RGC\/HKBU12201619"]}]},{"name":"General Research Fund from the Research Grant Council of Hong Kong SAR","award":["RGC\/HKBU12202220"],"award-info":[{"award-number":["RGC\/HKBU12202220"]}]},{"name":"General Research Fund from the Research Grant Council of Hong Kong SAR","award":["RGC\/HKBU12202417"],"award-info":[{"award-number":["RGC\/HKBU12202417"]}]},{"DOI":"10.13039\/501100001747","name":"Faculty Research Grant of Hong Kong Baptist University","doi-asserted-by":"publisher","award":["FRG2\/17-18\/027"],"award-info":[{"award-number":["FRG2\/17-18\/027"]}],"id":[{"id":"10.13039\/501100001747","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1109\/tnnls.2020.3015215","type":"journal-article","created":{"date-parts":[[2020,9,2]],"date-time":"2020-09-02T16:15:21Z","timestamp":1599063321000},"page":"3538-3552","source":"Crossref","is-referenced-by-count":12,"title":["Demystifying Deep Learning in Predictive Spatiotemporal Analytics: An Information-Theoretic Framework"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0831-7999","authenticated-orcid":false,"given":"Qi","family":"Tan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0166-3944","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8669-9064","authenticated-orcid":false,"given":"Jiming","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","first-page":"5","article-title":"An intuitive proof of the data processing inequality","volume":"12 nos","author":"beaudry","year":"2012","journal-title":"Quantum Info Comput"},{"key":"ref38","author":"cover","year":"2012","journal-title":"Elements of Information Theory"},{"key":"ref33","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc 27th Neural Inf Process Syst (NIPS)"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2891257"},{"key":"ref30","first-page":"2299","article-title":"Estimating information flow in deep neural networks","author":"goldfeld","year":"2019","journal-title":"Proc 36th Int Conf Mach Learn (ICML)"},{"key":"ref37","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc 3rd ICLR"},{"key":"ref36","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref35","first-page":"1863","article-title":"A clockwork RNN","author":"koutnik","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn (ICML)"},{"key":"ref34","first-page":"493","article-title":"Hierarchical recurrent neural networks for long-term dependencies","author":"hihi","year":"1996","journal-title":"Proc 8th Neural Inf Process Syst (NIPS)"},{"key":"ref60","first-page":"528","article-title":"Isometric projection","author":"cai","year":"2007","journal-title":"Proc 22nd AAAI"},{"key":"ref28","first-page":"13613","article-title":"Non-normal recurrent neural network (nnRNN): Learning long time dependencies while improving expressivity with transient dynamics","author":"kerg","year":"2019","journal-title":"Proc 32nd Neual Inf Process Syst (NeurIPS)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2910302"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITW.2015.7133169"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623624"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.23943\/princeton\/9780691128917.001.0001"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2018.03.002"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.80"},{"key":"ref21","first-page":"2588","article-title":"Deep multi-view spatial-temporal network for taxi demand prediction","author":"yao","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/476"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/366"},{"key":"ref26","first-page":"1","article-title":"Capacity and trainability in recurrent neural networks","author":"collins","year":"2017","journal-title":"Proc 5th ICLR"},{"key":"ref25","article-title":"Visualizing and understanding recurrent networks","author":"karpathy","year":"2015"},{"key":"ref50","first-page":"13978","article-title":"Generalization in reinforcement learning with selective noise injection and information bottleneck","author":"igl","year":"2019","journal-title":"Proc 32nd Neural Inf Process Syst (NeurIPS)"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMms1215400"},{"key":"ref59","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref58","first-page":"338","article-title":"Learning deep representation from big and heterogeneous data for traffic accident inference","author":"chen","year":"2016","journal-title":"Proc 30th AAAI Conf Artif Intell"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(88)90007-X"},{"key":"ref56","first-page":"8024","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc 33rd Neural Inf Process Syst (NeurIPS)"},{"key":"ref55","first-page":"5915","article-title":"Fast-slow recurrent neural networks","author":"mujika","year":"2017","journal-title":"Proc 31st Neural Inf Process Syst (NIPS)"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref53","author":"rasmussen","year":"2006","journal-title":"Gaussian Processes for Machine Learning"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1289\/ehp.6052"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5470"},{"key":"ref11","author":"gao","year":"2007","journal-title":"Multiscale Analysis of Complex Time Series Integration of Chaos and Random Fractal Theory and Beyond"},{"key":"ref40","first-page":"1522","article-title":"Factorized recurrent neural architectures for longer range dependence","author":"belletti","year":"2018","journal-title":"Proc 21st Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/e19060273"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/404"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1201\/b17115"},{"key":"ref15","first-page":"3901","article-title":"Predicting spatio-temporal propagation of seasonal influenza using variational Gaussian process regression","author":"senanayake","year":"2016","journal-title":"Proc 30th AAAI"},{"key":"ref16","first-page":"3491","article-title":"Fast multivariate spatio-temporal analysis via low rank tensor learning","author":"bahadori","year":"2014","journal-title":"Proc 27th Neural Inf Process Syst (NIPS)"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2017.146"},{"key":"ref18","first-page":"847","article-title":"Temporal regularized matrix factorization for high-dimensional time series prediction","author":"yu","year":"2016","journal-title":"Proc 29th Neural Inf Process Syst (NIPS)"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2832085"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783275"},{"key":"ref3","first-page":"493","article-title":"Modeling and mining spatiotemporal patterns of infection risk from heterogeneous data for active surveillance planning","author":"yang","year":"2014","journal-title":"Proc 28th AAAI Conf Artif Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TSTE.2019.2897136"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2869131"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313577"},{"key":"ref7","first-page":"1655","article-title":"Deep spatio-temporal residual networks for citywide crowd flows prediction","author":"zhang","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1276"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313704"},{"key":"ref46","first-page":"1","article-title":"On the information bottleneck theory of deep learning","author":"saxe","year":"2018","journal-title":"Proc 6th Int Conf Learn Represent (ICLR)"},{"key":"ref45","first-page":"1310","article-title":"On the difficulty of training recurrent neural networks","author":"pascanu","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn (ICML)"},{"key":"ref48","first-page":"1","article-title":"Mine: Mutual information neural estimation","author":"belghazi","year":"2018","journal-title":"Proc 35th Int Conf Mach Learn (ICML)"},{"key":"ref47","first-page":"1","article-title":"Deep variational information bottleneck","author":"alemi","year":"2017","journal-title":"Proc 5th Int Conf Learn Represent (ICLR)"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.69.066138"},{"key":"ref41","first-page":"165","article-title":"Information bottleneck for Gaussian variables,” J. Mach. Learn","volume":"6","author":"chechik","year":"2004","journal-title":"Res"},{"key":"ref44","first-page":"3570","article-title":"On orthogonality and learning recurrent networks with long term dependencies","author":"vorontsov","year":"2017","journal-title":"Proc 34th Int Conf Mach Learn (ICML)"},{"key":"ref43","article-title":"A simple way to initialize recurrent networks of rectified linear units","author":"le","year":"2015","journal-title":"arXiv 1504 00941"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9505270\/09185001.pdf?arnumber=9185001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:45:43Z","timestamp":1641987943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9185001\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":60,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.3015215","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8]]}}}