{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:48:27Z","timestamp":1766083707358,"version":"3.48.0"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"publisher","award":["W911NF-24-1-0127"],"award-info":[{"award-number":["W911NF-24-1-0127"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["#2318101"],"award-info":[{"award-number":["#2318101"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Cogn. Dev. Syst."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1109\/tcds.2025.3564285","type":"journal-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T13:08:00Z","timestamp":1745500080000},"page":"1436-1446","source":"Crossref","is-referenced-by-count":0,"title":["Delving Deeper Into Astromorphic Transformers"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-3509-8455","authenticated-orcid":false,"given":"Md Zesun Ahmed","family":"Mia","sequence":"first","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0287-2139","authenticated-orcid":false,"given":"Malyaban","family":"Bal","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5545-4494","authenticated-orcid":false,"given":"Abhronil","family":"Sengupta","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, The Pennsylvania State University, University Park, PA, USA"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1186\/s13064-020-00151-9"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s12021-023-09622-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2020.00912"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tins.2021.07.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2019.00092"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-06936-9"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3335450\/mm1"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2008.02.001"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1002\/glia.23250"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2019.00095"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3067593"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2854291"},{"key":"ref13","article-title":"On the self-repair role of astrocytes in STDP enabled unsupervised SNNs","volume-title":"Front. Neurosci.","volume":"14","author":"Rastogi","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i6.25947"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2673021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2015.00099"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01940"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2219150120"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref20"},{"article-title":"Improving language understanding by generative pre-training","year":"2018","author":"Radford","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2018.00774"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.12.002"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1677-2"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01086"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2726060"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2023.3329532"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.2023.3300318"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s10825-015-0703-3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2017.06.071"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2021.699632"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2012.00076"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2020.603796"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/ac5d1f"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3407197.3407205"},{"key":"ref36","first-page":"9355","article-title":"Linear transformers are secretly fast weight programmers","volume-title":"Proc. Int. Conf. on Mach. Learn. (PMLR)","author":"Schlag","year":"2021"},{"key":"ref37","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Katharopoulos","year":"2020"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3465055"},{"article-title":"Fast and accurate deep network learning by exponential linear units (ELUS)","year":"2015","author":"Clevert","key":"ref39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1006\/jtbi.1994.1041"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2007.19.2.303"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1088\/1478-3967\/1\/1\/004"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1088\/1478-3975\/4\/1\/001"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0029445"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/S0301-0082(02)00080-1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2010.08.043"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2012.00076"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10867-009-9155-y"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1152\/physrev.00049.2005"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref51","article-title":"Stand-alone self-attention in vision models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Ramachandran","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1088\/2634-4386\/acb2f0"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICSAI53574.2021.9664146"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1002\/int.22772"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-10336-3"},{"article-title":"Coupled oscillatory recurrent neural network (CORNN): An accurate and (gradient) stable architecture for learning long time dependencies","year":"2020","author":"Rusch","key":"ref56"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/AICAS51828.2021.9458402"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/LSSC.2021.3092727"},{"key":"ref59","first-page":"9168","article-title":"UnICORNN: A recurrent model for learning very long time dependencies","volume-title":"Proc. Int. Conf. Mach. Learn. (PMLR)","author":"Rusch","year":"2021"},{"article-title":"BioLeaF: A bioplausible learning framework for training of spiking neural networks","year":"2021","author":"Yang","key":"ref60"},{"article-title":"SpikingFormer: spike-driven residual learning for transformer-based spiking neural network","year":"2023","author":"Zhou","key":"ref61"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053914"},{"article-title":"Advancing residual learning towards powerful deep spiking neural networks","year":"2021","author":"Hu","key":"ref63"},{"article-title":"SpikFormer: When spiking neural network meets transformer","year":"2022","author":"Zhou","key":"ref64"},{"key":"ref65","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proc. 49th Ann. Meet. Assoc. Computat. Linguistics: Human Lang. Technol.","author":"Maas","year":"2011"},{"article-title":"Learning Multiple Layers of Features from Tiny Images","year":"2009","author":"Krizhevsky","key":"ref66"},{"key":"ref67","first-page":"1072","article-title":"Pointer sentinel mixture models","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Merity","year":"2017"},{"key":"ref68","first-page":"3965","article-title":"CoatNet: Marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref69","first-page":"1532","article-title":"GLOVE: Global vectors for word representation","volume-title":"Proc. Empirical Methods Natural Lang. Process. (EMNLP)","author":"Pennington","year":"2014"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1489"},{"article-title":"Breaking the Softmax bottleneck: a high-rank RNN language model","year":"2017","author":"Yang","key":"ref71"},{"article-title":"Learning associative inference using fast weight memory","year":"2020","author":"Schlag","key":"ref72"},{"key":"ref73","first-page":"5000","article-title":"Deep residual output layers for neural language generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pappas","year":"2019"},{"article-title":"Language models with transformers","year":"2019","author":"Wang","key":"ref74"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2789723"},{"key":"ref76","first-page":"1","article-title":"ReTransformer: ReRAM-based processing-in-memory architecture for transformer acceleration","volume-title":"Proc. 39th Int. Conf. Comput.-Aided Des.","author":"Yang","year":"2020"}],"container-title":["IEEE Transactions on Cognitive and Developmental Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/7274989\/11288412\/10976578-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7274989\/11288412\/10976578.pdf?arnumber=10976578","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T18:35:19Z","timestamp":1766082919000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10976578\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":76,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcds.2025.3564285","relation":{},"ISSN":["2379-8920","2379-8939"],"issn-type":[{"type":"print","value":"2379-8920"},{"type":"electronic","value":"2379-8939"}],"subject":[],"published":{"date-parts":[[2025,12]]}}}