{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T19:23:32Z","timestamp":1740165812328,"version":"3.37.3"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T00:00:00Z","timestamp":1709251200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2020AAA0109401"],"award-info":[{"award-number":["2020AAA0109401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["61921006","62176117"],"award-info":[{"award-number":["61921006","62176117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Collaborative Innovation Center of Novel Software Technology and Industrialization"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2024,3]]},"DOI":"10.1109\/tnnls.2022.3195909","type":"journal-article","created":{"date-parts":[[2023,7,26]],"date-time":"2023-07-26T18:39:57Z","timestamp":1690396797000},"page":"3674-3688","source":"Crossref","is-referenced-by-count":0,"title":["Theoretical Exploration of Flexible Transmitter Model"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4164-4617","authenticated-orcid":false,"given":"Jin-Hui","family":"Wu","sequence":"first","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0614-8984","authenticated-orcid":false,"given":"Shao-Qun","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Jiang","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0746-1494","authenticated-orcid":false,"given":"Zhi-Hua","family":"Zhou","sequence":"additional","affiliation":[{"name":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2021.624694"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fcomp.2021.786964"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/BF02478259"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1952.sp004764"},{"issue":"253","key":"ref7","first-page":"1","article-title":"Bifurcation spiking neural network","volume":"22","author":"Zhang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF02551274"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90003-8"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80131-5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155422"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(05)80125-X"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/81.841860"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSII.2005.852006"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/11840817_66"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2019.06.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.1993.394188"},{"key":"ref19","article-title":"The universal approximation theorem for complex-valued neural networks","author":"Voigtlaender","year":"2020","journal-title":"arXiv:2012.03351"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/18.256500"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF02836480"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.6.1262"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1147\/rd.383.0277"},{"key":"ref24","first-page":"907","article-title":"The power of depth for feedforward neural networks","volume-title":"Proc. 29th Conf. Learn. Theory","author":"Eldan"},{"key":"ref25","first-page":"2979","article-title":"Depth-width tradeoffs in approximating natural functions with neural networks","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Safran"},{"key":"ref26","first-page":"1517","article-title":"Benefits of depth in neural networks","volume-title":"Proc. 29th Conf. Learn. Theory","author":"Telgarsky"},{"key":"ref27","first-page":"6232","article-title":"The expressive power of neural networks: A view from the width","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.03.024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155333"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/72.165604"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/72.410380"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3477.678658"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3305950"},{"key":"ref34","first-page":"853","article-title":"Elimination of all bad local minima in deep learning","volume-title":"Proc. 23rd Int. Conf. Artif. Intell. Statist.","author":"Kawaguchi"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.06.009"},{"key":"ref36","first-page":"3730","article-title":"Optimization landscape and expressivity of deep CNNs","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Nguyen"},{"key":"ref37","first-page":"586","article-title":"Deep learning without poor local minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kawaguchi"},{"key":"ref38","first-page":"2902","article-title":"Deep linear networks with arbitrary loss: All local minima are global","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Laurent"},{"article-title":"On the loss landscape of a class of deep neural networks with no bad local valleys","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Nguyen","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/34.107014"},{"article-title":"Gradient descent provably optimizes over-parameterized neural networks","volume-title":"Proc. 6th Int. Conf. Learn. Represent.","author":"Du","key":"ref41"},{"key":"ref42","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref43","first-page":"8168","article-title":"Learning overparameterized neural networks via stochastic gradient descent on structured data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref44","first-page":"6676","article-title":"On the convergence rate of training recurrent neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Allen-Zhu"},{"key":"ref45","first-page":"1675","article-title":"Gradient descent finds global minima of deep neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Du"},{"key":"ref46","first-page":"242","article-title":"A convergence theory for deep learning via over-parameterization","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Allen-Zhu"},{"key":"ref47","first-page":"2055","article-title":"An improved analysis of training over-parameterized deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zou"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-019-05839-6"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2021.12.009"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3023-7"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-2885-6"},{"key":"ref52","article-title":"On complex valued convolutional neural networks","author":"Guberman","year":"2016","journal-title":"arXiv:1602.09046"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1969.300225"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3045390.3045509"},{"article-title":"Deep complex networks","volume-title":"Proc. 5th Int. Conf. Learn. Represent.","author":"Trabelsi","key":"ref55"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-022-2900-0"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwac123"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1090\/chel\/368"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2307\/1913643"},{"key":"ref60","first-page":"2835","article-title":"Understanding the loss surface of neural networks for binary classification","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Liang"},{"key":"ref61","first-page":"2004","article-title":"Learning ReLUs via gradient descent","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Soltanolkotabi"},{"key":"ref62","first-page":"4355","article-title":"Adding one neuron can eliminate all bad local minima","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2021.1228"},{"key":"ref64","volume-title":"Complex Analysis","volume":"2","author":"Stein","year":"2010"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/10454107\/10195872.pdf?arnumber=10195872","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T16:11:51Z","timestamp":1709309511000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10195872\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3]]},"references-count":64,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2022.3195909","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"type":"print","value":"2162-237X"},{"type":"electronic","value":"2162-2388"}],"subject":[],"published":{"date-parts":[[2024,3]]}}}