{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:50:19Z","timestamp":1773247819398,"version":"3.50.1"},"reference-count":31,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T00:00:00Z","timestamp":1708473600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Neurosci."],"abstract":"<jats:p>The field of wireless communication is currently being pushed to new boundaries with the emergence of 6G technology. This advanced technology requires substantially increased data rates and processing speeds while simultaneously requiring energy-efficient solutions for real-world practicality. In this work, we apply a neuroscience-inspired machine learning model called echo state network (ESN) to the critical task of symbol detection in massive MIMO-OFDM systems, a key technology for 6G networks. Our work encompasses the design of a hardware-accelerated reservoir neuron architecture to speed up the ESN-based symbol detector. The design is then validated through a proof of concept on the Xilinx Virtex-7 FPGA board in real-world scenarios. The experiment results show the great performance and scalability of our symbol detector design across a range of MIMO configurations, compared with traditional MIMO symbol detection methods like linear minimum mean square error. Our findings also confirm the performance and feasibility of our entire system, reflected in low bit error rates, low resource utilization, and high throughput.<\/jats:p>","DOI":"10.3389\/fncom.2024.1345644","type":"journal-article","created":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T11:26:27Z","timestamp":1708514787000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Leveraging neuro-inspired AI accelerator for high-speed computing in 6G networks"],"prefix":"10.3389","volume":"18","author":[{"given":"Chunxiao","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Farhan","family":"Azmine","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yibin","family":"Liang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2024,2,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"137","DOI":"10.1007\/s11265-007-0140-z","article-title":"Low-error, high-speed approximation of the sigmoid function for large FPGA implementations","volume":"52","author":"Bajger","year":"2008","journal-title":"J. Signal Process. Syst"},{"key":"B2","doi-asserted-by":"publisher","first-page":"440","DOI":"10.1016\/j.neunet.2011.02.002","article-title":"Architectural and markovian factors of echo state networks","volume":"24","author":"Gallicchio","year":"2011","journal-title":"Neural Netw"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3440017","article-title":"A cost-efficient digital ESN architecture on FPGA for OFDM symbol detection","volume":"17","author":"Gan","year":"2021","journal-title":"ACM J. Emerg. Technol. Comp. Syst"},{"key":"B4","doi-asserted-by":"publisher","first-page":"852","DOI":"10.1109\/LWC.2018.2832128","article-title":"Deep learning-based channel estimation for beamspace mmwave massive MIMO systems","volume":"7","author":"He","year":"2018","journal-title":"IEEE Wireless Commun. Lett"},{"key":"B5","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1109\/MCOM.001.2001187","article-title":"Toward a 6G AI-native air interface","volume":"59","author":"Hoydis","year":"2021","journal-title":"IEEE Commun. Mag"},{"key":"B6","doi-asserted-by":"publisher","first-page":"4575","DOI":"10.1007\/s10462-021-10113-0","article-title":"A survey paper on design and implementation of multipliers for digital system applications","volume":"55","author":"Immareddy","year":"2022","journal-title":"Artif. Intell. Rev"},{"key":"B7","first-page":"13","volume-title":"The \u201cEcho State\u201d Approach to Analysing and Training Recurrent Neural Networks-With an Erratum Note","author":"Jaeger","year":"2001"},{"key":"B8","first-page":"609","article-title":"Adaptive nonlinear system identification with echo state networks","volume":"15","author":"Jaeger","year":"2002","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1126\/science.1091277","article-title":"Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication","volume":"304","author":"Jaeger","year":"2004","journal-title":"Science"},{"key":"B10","doi-asserted-by":"crossref","first-page":"2068","DOI":"10.1109\/INFOCOM48880.2022.9796854","article-title":"Real-time machine learning for symbol detection in MIMO-OFDM systems","volume-title":"IEEE INFOCOM 2022-IEEE Conference on Computer Communications","author":"Liang","year":"2022"},{"key":"B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ISQED54688.2022.9806247","article-title":"FPGA-based reservoir computing with optimized reservoir node architecture","volume-title":"2022 23rd International Symposium on Quality Electronic Design (ISQED)","author":"Lin","year":"2022"},{"key":"B12","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1016\/j.dcan.2021.09.014","article-title":"Toward intelligent wireless communications: Deep learning-based physical layer technologies","volume":"7","author":"Liu","year":"2021","journal-title":"Digit. Commun. Netw"},{"key":"B13","doi-asserted-by":"publisher","first-page":"365","DOI":"10.1007\/s13218-012-0204-5","article-title":"Reservoir computing trends","volume":"26","author":"Luko\u0161evi\u010dius","year":"2012","journal-title":"K\u00fcnstliche Intelligenz"},{"key":"B14","doi-asserted-by":"publisher","first-page":"3590","DOI":"10.1109\/TWC.2010.092810.091092","article-title":"Noncooperative cellular wireless with unlimited numbers of base station antennas","volume":"9","author":"Marzetta","year":"2010","journal-title":"IEEE Transact. Wireless Commun"},{"key":"B15","doi-asserted-by":"publisher","first-page":"4694","DOI":"10.1109\/TNNLS.2017.2766162","article-title":"Brain-inspired wireless communications: where reservoir computing meets MIMO-OFDM","volume":"29","author":"Mosleh","year":"2017","journal-title":"IEEE Transact. Neural Netw. Learn. Syst"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.08691","article-title":"Channel estimation in massive MIMO systems","author":"Neumann","year":"2015","journal-title":"arXiv"},{"key":"B17","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1109\/MWC.2019.1800601","article-title":"Deep learning in physical layer communications","volume":"26","author":"Qin","year":"2019","journal-title":"IEEE Wireless Communications"},{"key":"B18","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1109\/MSP.2011.2178495","article-title":"Scaling up mimo: Opportunities and challenges with very large arrays","volume":"30","author":"Rusek","year":"2012","journal-title":"IEEE Signal Process. Mag"},{"key":"B19","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1109\/MNET.001.1900287","article-title":"A vision of 6g wireless systems: applications, trends, technologies, and open research problems","volume":"34","author":"Saad","year":"2019","journal-title":"IEEE Netw"},{"key":"B20","doi-asserted-by":"crossref","first-page":"45","DOI":"10.1007\/978-3-030-03508-2_2","volume-title":"5g Applications and Architectures. 5G Enabled Secure Wireless Networks","author":"Sah","year":"2019"},{"key":"B21","first-page":"1","article-title":"Realizing green symbol detection via reservoir computing: an energy-efficiency perspective","volume-title":"2018 IEEE International Conference on Communications (ICC)","author":"Shafin","year":"2018"},{"key":"B22","doi-asserted-by":"publisher","first-page":"4044","DOI":"10.1109\/TWC.2021.3055202","article-title":"Deep learning for distributed channel feedback and multiuser precoding in FDD massive MIMO","volume":"20","author":"Sohrabi","year":"2021","journal-title":"IEEE Transact. Wireless Commun"},{"key":"B23","doi-asserted-by":"publisher","first-page":"754","DOI":"10.1109\/TCOMM.2002.1006557","article-title":"Turbo equalization: Principles and new results","volume":"50","author":"Tuchler","year":"","journal-title":"IEEE Transact. Commun"},{"key":"B24","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1109\/78.984761","article-title":"Minimum mean squared error equalization using a priori information","volume":"50","author":"Tuchler","year":"","journal-title":"IEEE Transact. Signal Process"},{"key":"B25","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1109\/CC.2017.8233654","article-title":"Deep learning for wireless physical layer: opportunities and challenges","volume":"14","author":"Wang","year":"2017","journal-title":"China Commun"},{"key":"B26","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1109\/LWC.2018.2818160","article-title":"Deep learning for massive MIMO CSI feedback","volume":"7","author":"Wen","year":"2018","journal-title":"IEEE Wireless Commun. Lett"},{"key":"B27","doi-asserted-by":"publisher","first-page":"916","DOI":"10.1109\/JSTSP.2014.2313021","article-title":"Large-scale MIMO detection for 3GPP LTE: Algorithms and FPGA implementations","volume":"8","author":"Wu","year":"2014","journal-title":"IEEE J. Sel. Top. Signal Process"},{"key":"B28","doi-asserted-by":"publisher","first-page":"7313","DOI":"10.1109\/ACCESS.2016.2623772","article-title":"An overview of low-rank channel estimation for massive MIMO systems","volume":"4","author":"Xie","year":"2016","journal-title":"IEEE Access"},{"key":"B29","volume-title":"7 Series DSP48E1 Slice User Guide (UG479)","year":"2018"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1266","DOI":"10.1609\/aaai.v34i01.5481","article-title":"Deep reservoir computing meets 5G MIMO-OFDM systems in symbol detection","volume":"34","author":"Zhou","year":"","journal-title":"Proc. AAAI Conf. Artif. Intell"},{"key":"B31","doi-asserted-by":"publisher","first-page":"3712","DOI":"10.1109\/TWC.2020.2976004","article-title":"Learning for detection: MIMO-OFDM symbol detection through downlink pilots","volume":"19","author":"Zhou","year":"","journal-title":"IEEE Transact. Wireless Commun"}],"container-title":["Frontiers in Computational Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1345644\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T11:26:35Z","timestamp":1708514795000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fncom.2024.1345644\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,21]]},"references-count":31,"alternative-id":["10.3389\/fncom.2024.1345644"],"URL":"https:\/\/doi.org\/10.3389\/fncom.2024.1345644","relation":{},"ISSN":["1662-5188"],"issn-type":[{"value":"1662-5188","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,21]]},"article-number":"1345644"}}