{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:36:09Z","timestamp":1730230569466,"version":"3.28.0"},"reference-count":34,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,6]],"date-time":"2021-06-06T00:00:00Z","timestamp":1622937600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,6,6]]},"DOI":"10.1109\/icassp39728.2021.9413450","type":"proceedings-article","created":{"date-parts":[[2021,5,13]],"date-time":"2021-05-13T19:53:45Z","timestamp":1620935625000},"page":"2950-2954","source":"Crossref","is-referenced-by-count":1,"title":["Wearing A Mask: Compressed Representations of Variable-Length Sequences Using Recurrent Neural Tangent Kernels"],"prefix":"10.1109","author":[{"given":"Sina","family":"Alemohammad","sequence":"first","affiliation":[]},{"given":"Hossein","family":"Babaei","sequence":"additional","affiliation":[]},{"given":"Randall","family":"Balestriero","sequence":"additional","affiliation":[]},{"given":"Matt Y.","family":"Cheung","sequence":"additional","affiliation":[]},{"given":"Ahmed Imtiaz","family":"Humayun","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"LeJeune","sequence":"additional","affiliation":[]},{"given":"Naiming","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Lorenzo","family":"Luzi","sequence":"additional","affiliation":[]},{"given":"Jasper","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Zichao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Richard G.","family":"Baraniuk","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"article-title":"Pearson distance is not a distance","year":"2019","author":"solo","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BFb0020217"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1002\/wics.101"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/0364-0213(90)90002-E"},{"key":"ref34","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.04.025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2013.11.045"},{"key":"ref12","first-page":"1631","article-title":"Recursive deep models for semantic compositionality over a sentiment treebank","author":"socher","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Language Process (EMNLP)"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2017.8081508"},{"key":"ref15","first-page":"8571","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","author":"jacot","year":"2018","journal-title":"Advances in neural information processing systems"},{"article-title":"The recurrent neural tangent kernel","year":"2020","author":"alemohammad","key":"ref16"},{"article-title":"Tensor programs ii: Neural tangent kernel for any architecture","year":"2020","author":"yang","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/11840817_66"},{"key":"ref19","article-title":"A max-affine spline perspective of recurrent neural networks","author":"wang","year":"2018","journal-title":"Int Conf Learn Representations"},{"key":"ref28","first-page":"6155","article-title":"Learning and generalization in overparameterized neural networks, going beyond two layers","author":"allen-zhu","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2007.367023"},{"key":"ref27","first-page":"6676","article-title":"On the convergence rate of training recurrent neural networks","author":"allen-zhu","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(94)90029-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"article-title":"Stochastic gradient descent optimizes overparameterized deep relu networks","year":"2018","author":"zou","key":"ref29"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-33037-0_14"},{"key":"ref8","first-page":"536","article-title":"Kernel pca and de-noising in feature spaces","author":"mika","year":"1999","journal-title":"Advances Neural Inf Process Syst"},{"key":"ref7","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1198\/106186006X113430"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1049\/el:20046791"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref20","first-page":"374","article-title":"A spline theory of deep learning","volume":"80","author":"balestriero","year":"2018","journal-title":"Mach Learn Res"},{"key":"ref22","first-page":"202","article-title":"Avoiding pathologies in very deep networks","author":"duvenaud","year":"2014","journal-title":"Artificial Intelligence and Statistics"},{"key":"ref21","article-title":"Deep neural networks as gaussian processes","author":"lee","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref24","article-title":"Deep convolutional networks as shallow gaussian processes","author":"garriga-alonso","year":"2019","journal-title":"Int Conf Learn Representations"},{"key":"ref23","article-title":"Bayesian deep convolutional networks with many channels are gaussian processes","author":"novak","year":"2019","journal-title":"Int Conf Learn Representations"},{"key":"ref26","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","author":"du","year":"2019","journal-title":"Int Conf Mach Learn"},{"article-title":"Tensor programs i: Wide feedforward or recurrent neural networks of any architecture are gaussian processes","year":"2019","author":"yang","key":"ref25"}],"event":{"name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2021,6,6]]},"location":"Toronto, ON, Canada","end":{"date-parts":[[2021,6,11]]}},"container-title":["ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9413349\/9413350\/09413450.pdf?arnumber=9413450","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T15:41:11Z","timestamp":1652197271000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9413450\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,6]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/icassp39728.2021.9413450","relation":{},"subject":[],"published":{"date-parts":[[2021,6,6]]}}}