{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:58:36Z","timestamp":1780675116656,"version":"3.54.1"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T00:00:00Z","timestamp":1712620800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["Young Faculty Award"],"award-info":[{"award-number":["Young Faculty Award"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2127780"],"award-info":[{"award-number":["2127780"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2235472"],"award-info":[{"award-number":["2235472"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2312517"],"award-info":[{"award-number":["2312517"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2319198"],"award-info":[{"award-number":["2319198"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["2321840"],"award-info":[{"award-number":["2321840"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000028","name":"Semiconductor Research Corporation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000028","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-21-1-2225"],"award-info":[{"award-number":["N00014-21-1-2225"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["N00014-22-1-2067"],"award-info":[{"award-number":["N00014-22-1-2067"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000006","name":"Office of Naval Research","doi-asserted-by":"publisher","award":["Young Investigator Program Award"],"award-info":[{"award-number":["Young Investigator Program Award"]}],"id":[{"id":"10.13039\/100000006","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000181","name":"Air Force Office of Scientific Research","doi-asserted-by":"publisher","award":["FA9550-22-1-0253"],"award-info":[{"award-number":["FA9550-22-1-0253"]}],"id":[{"id":"10.13039\/100000181","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100004351","name":"Cisco Systems","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100004351","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Brain-inspired computing has become an emerging field, where a growing number of works focus on developing algorithms that bring machine learning closer to human brains at the functional level. As one of the promising directions, Hyperdimensional Computing (HDC) is centered around the idea of having holographic and high-dimensional representation as the neural activities in our brains. Such representation is the fundamental enabler for the efficiency and robustness of HDC. However, existing HDC-based algorithms suffer from limitations within the encoder. To some extent, they all rely on manually selected encoders, meaning that the resulting representation is never adapted to the tasks at hand.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>In this paper, we propose FLASH, a novel hyperdimensional learning method that incorporates an adaptive and learnable encoder design, aiming at better overall learning performance while maintaining good properties of HDC representation. Current HDC encoders leverage Random Fourier Features (RFF) for kernel correspondence and enable locality-preserving encoding. We propose to learn the encoder matrix distribution via gradient descent and effectively adapt the kernel for a more suitable HDC encoding.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Our experiments on various regression datasets show that tuning the HDC encoder can significantly boost the accuracy, surpassing the current HDC-based algorithm and providing faster inference than other baselines, including RFF-based kernel ridge regression.<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The results indicate the importance of an adaptive encoder and customized high-dimensional representation in HDC.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1371988","type":"journal-article","created":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T14:37:32Z","timestamp":1712673452000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["Hyperdimensional computing with holographic and adaptive encoder"],"prefix":"10.3389","volume":"7","author":[{"given":"Alejandro","family":"Hern\u00e1ndez-Cano","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuowen","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Zakeri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohsen","family":"Imani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2024,4,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/ICCAD57390.2023.10323671","author":"Barkam","year":""},{"key":"B2","first-page":"1","article-title":"\u201cHdgim: hyperdimensional genome sequence matching on unreliable highly scaled fefet,\u201d","volume-title":"2023 Design, Automation &Test in Europe Conference &Exhibition (DATE)","author":"Barkam","year":""},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549437","article-title":"\u201cDarl: distributed reconfigurable accelerator for hyperdimensional reinforcement learning,\u201d","author":"Chen","year":"2022","journal-title":"Proceedings of the 41st IEEE\/ACM International Conference on Computer-Aided Design"},{"key":"B4","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1109\/FPL60245.2023.00013","article-title":"\u201cHypergraf: Hyperdimensional graph-based reasoning acceleration on fpga,\u201d","volume-title":"2023 33rd International Conference on Field-Programmable Logic and Applications (FPL)","author":"Chen","year":"2023"},{"key":"B5","article-title":"\u201cSaga: a fast incremental gradient method with support for non-strongly convex composite objectives,\u201d","author":"Defazio","year":"2014","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1145\/3517343.3522597","article-title":"\u201cComputing on functions using randomized vector representations (in brief),\u201d","author":"Frady","year":"2022","journal-title":"Proceedings of the 2022 Annual Neuro-Inspired Computational Elements Conference"},{"key":"B7","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1109\/TNNLS.2021.3105949","article-title":"Variable binding for sparse distributed representations: theory and applications","volume":"34","author":"Frady","year":"2021","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1214\/aos\/1176347963","article-title":"Multivariate adaptive regression splines","volume":"19","author":"Friedman","year":"1991","journal-title":"Ann. Statist"},{"key":"B9","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1109\/MCAS.2020.2988388","article-title":"Classification using hyperdimensional computing: a review","volume":"20","author":"Ge","year":"2020","journal-title":"IEEE Circ. Syst. Magaz"},{"key":"B10","doi-asserted-by":"crossref","first-page":"56","DOI":"10.23919\/DATE51398.2021.9474107","article-title":"\u201cOnlinehd: robust, efficient, and single-pass online learning using hyperdimensional system,\u201d","volume-title":"2021 Design, Automation &Test in Europe Conference &Exhibition (DATE)","author":"Hernandez-Cane","year":"2021"},{"key":"B11","doi-asserted-by":"crossref","first-page":"7","DOI":"10.1109\/DAC18074.2021.9586284","article-title":"\u201cReghd: robust and efficient regression in hyper-dimensional learning system,\u201d","volume-title":"2021 58th ACM\/IEEE Design Automation Conference (DAC)","author":"Hern\u00e1ndez-Cano","year":"2021"},{"key":"B12","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1038\/s42256-023-00630-8","article-title":"A neuro-vector-symbolic architecture for solving raven's progressive matrices","volume":"5","author":"Hersche","year":"2023","journal-title":"Nat. Mach. Intell"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317785","article-title":"\u201cBric: locality-based encoding for energy-efficient brain-inspired hyperdimensional computing,\u201d","author":"Imani","year":"2019","journal-title":"Proceedings of the 56th Annual Design Automation Conference 2019"},{"key":"B14","doi-asserted-by":"crossref","first-page":"652","DOI":"10.1109\/ICCD56317.2022.00100","article-title":"\u201cHyperdimensional hybrid learning on end-edge-cloud networks,\u201d","volume-title":"2022 IEEE 40th International Conference on Computer Design (ICCD)","author":"Issa","year":"2022"},{"key":"B15","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/s12559-009-9009-8","article-title":"Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors","volume":"1","author":"Kanerva","year":"2009","journal-title":"Cogn. Comput"},{"key":"B16","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/s41928-020-0410-3","article-title":"In-memory hyperdimensional computing","volume":"3","author":"Karunaratne","year":"2020","journal-title":"Nat. Electr"},{"key":"B17","article-title":"Vector symbolic architectures as a computing framework for nanoscale hardware","author":"Kleyko","year":"2021","journal-title":"arXiv preprint arXiv:2106.05268"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3558000","article-title":"A survey on hyperdimensional computing aka vector symbolic architectures, part ii: applications, cognitive models, and challenges","volume":"55","author":"Kleyko","year":"2023","journal-title":"ACM Comput. Surv"},{"key":"B19","doi-asserted-by":"publisher","first-page":"5880","DOI":"10.1109\/TNNLS.2018.2814400","article-title":"Classification and recall with binary hyperdimensional computing: tradeoffs in choice of density and mapping characteristics","volume":"29","author":"Kleyko","year":"2018","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B20","article-title":"\u201cInference for the generalization error,\u201d","author":"Nadeau","year":"1999","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1145\/3583781.3590298","article-title":"\u201cEfficient off-policy reinforcement learning via brain-inspired computing,\u201d","author":"Ni","year":"","journal-title":"Proceedings of the Great Lakes Symposium on VLSI 2023"},{"key":"B22","first-page":"01","article-title":"\u201cBrain-inspired trustworthy hyperdimensional computing with efficient uncertainty quantification,\u201d","volume-title":"2023 IEEE\/ACM International Conference on Computer Aided Design (ICCAD)","author":"Ni","year":""},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530668","article-title":"\u201cHdpg: Hyperdimensional policy-based reinforcement learning for continuous control,\u201d","author":"Ni","year":"","journal-title":"Proceedings of the 59th ACM\/IEEE Design Automation Conference"},{"key":"B24","first-page":"292","article-title":"\u201cAlgorithm-hardware co-design for efficient brain-inspired hyperdimensional learning on edge,\u201d","volume-title":"2022 Design, Automation &Test in Europe Conference &Exhibition (DATE)","author":"Ni","year":""},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1145\/3508352.3549477","article-title":"\u201cNeurally-inspired hyperdimensional classification for efficient and robust biosignal processing,\u201d","author":"Ni","year":"","journal-title":"Proceedings of the 41st IEEE\/ACM International Conference on Computer-Aided Design"},{"key":"B26","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1145\/355984.355989","article-title":"Lsqr: an algorithm for sparse linear equations and sparse least squares","volume":"8","author":"Paige","year":"1982","journal-title":"ACM Trans. Mathem. Softw"},{"key":"B27","doi-asserted-by":"crossref","first-page":"1688","DOI":"10.1109\/BIBM55620.2022.9995107","article-title":"\u201cExg signal feature selection using hyperdimensional computing encoding,\u201d","volume-title":"2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","author":"Pale","year":"2022"},{"key":"B28","doi-asserted-by":"publisher","first-page":"246","DOI":"10.1162\/neco.1991.3.2.246","article-title":"Universal approximation using radial-basis-function networks","volume":"3","author":"Park","year":"1991","journal-title":"Neur. Comput"},{"key":"B29","doi-asserted-by":"publisher","first-page":"757125","DOI":"10.3389\/fnins.2022.757125","article-title":"Graphd: Graph-based hyperdimensional memorization for brain-like cognitive learning","volume":"16","author":"Poduval","year":"","journal-title":"Front. Neurosci"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1145\/3489517.3530659","article-title":"\u201cAdaptive neural recovery for highly robust brain-like representation,\u201d","author":"Poduval","year":"","journal-title":"Proceedings of the 59th ACM\/IEEE Design Automation Conference"},{"key":"B31","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s10559-015-9723-z","article-title":"Formation of similarity-reflecting binary vectors with random binary projections","volume":"51","author":"Rachkovskij","year":"2015","journal-title":"Cybern. Syst. Analy"},{"key":"B32","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ICRC.2016.7738683","article-title":"\u201cHyperdimensional biosignal processing: a case study for emg-based hand gesture recognition,\u201d","volume-title":"2016 IEEE International Conference on Rebooting Computing (ICRC)","author":"Rahimi","year":"2016"},{"key":"B33","article-title":"\u201cRandom features for large-scale kernel machines,\u201d","author":"Rahimi","year":"2007","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B34","doi-asserted-by":"publisher","first-page":"958","DOI":"10.1007\/s11036-017-0942-6","article-title":"Hyperdimensional computing for blind and one-shot classification of EEG error-related potentials","volume":"25","author":"Rahimi","year":"2020","journal-title":"Mobile Netw. Applic"},{"key":"B35","doi-asserted-by":"publisher","first-page":"607","DOI":"10.1038\/s41586-019-1677-2","article-title":"Towards spike-based machine intelligence with neuromorphic computing","volume":"575","author":"Roy","year":"2019","journal-title":"Nature"},{"key":"B36","volume-title":"Fourier Analysis on Groups","author":"Rudin","year":"2017"},{"key":"B37","article-title":"Theoretical foundations of hyperdimensional computing","author":"Thomas","year":"2020","journal-title":"arXiv preprint arXiv:2010.07426"},{"key":"B38","doi-asserted-by":"publisher","first-page":"49","DOI":"10.1145\/2641190.2641198","article-title":"Openml: networked science in machine learning","volume":"15","author":"Vanschoren","year":"2013","journal-title":"SIGKDD Explor"},{"key":"B39","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1145\/3489517.3530395","article-title":"\u201cOdhd: one-class brain-inspired hyperdimensional computing for outlier detection,\u201d","author":"Wang","year":"2022","journal-title":"Proceedings of the 59th ACM\/IEEE Design Automation Conference"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527422","article-title":"\u201cBiohd: an efficient genome sequence search platform using hyperdimensional memorization,\u201d","author":"Zou","year":"2022","journal-title":"Proceedings of the 49th Annual International Symposium on Computer Architecture"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1371988\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T14:37:49Z","timestamp":1712673469000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1371988\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,9]]},"references-count":40,"alternative-id":["10.3389\/frai.2024.1371988"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1371988","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,9]]},"article-number":"1371988"}}