{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T20:03:43Z","timestamp":1787169823122,"version":"build-2736575974"},"reference-count":32,"publisher":"MIT Press","issue":"12","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,11,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Hyperdimensional computing (HDC) has become popular for light-weight and energy-efficient machine learning, suitable for wearable Internet-of-Things devices and near-sensor or on-device processing. HDC is computationally less complex than traditional deep learning algorithms and achieves moderate to good classification performance. This letter proposes to extend the training procedure in HDC by taking into account not only wrongly classified samples but also samples that are correctly classified by the HDC model but with low confidence. We introduce a confidence threshold that can be tuned for each data set to achieve the best classification accuracy. The proposed training procedure is tested on UCIHAR, CTG, ISOLET, and HAND data sets for which the performance consistently improves compared to the baseline across a range of confidence threshold values. The extended training procedure also results in a shift toward higher confidence values of the correctly classified samples, making the classifier not only more accurate but also more confident about its predictions.<\/jats:p>","DOI":"10.1162\/neco_a_01618","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T17:31:45Z","timestamp":1697477505000},"page":"2006-2023","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":14,"title":["Training a Hyperdimensional Computing Classifier Using a Threshold on Its Confidence"],"prefix":"10.1162","volume":"35","author":[{"given":"Laura","family":"Smets","sequence":"first","affiliation":[{"name":"Department of Computer Science, IDLab (University of Antwerp -- imec), 2000 Antwerp, Belgium Laura.Smets@uantwerpen.be"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Werner","family":"Van Leekwijck","sequence":"additional","affiliation":[{"name":"Department of Computer Science, IDLab (University of Antwerp -- imec), 2000 Antwerp, Belgium Werner.Vanleekwijck@uantwerpen.be"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ing Jyh","family":"Tsang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, IDLab (University of Antwerp -- imec), 2000 Antwerp, Belgium Inton.Tsang@imec.be"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Steven","family":"Latr\u00e9","sequence":"additional","affiliation":[{"name":"Department of Computer Science, IDLab (University of Antwerp -- imec), 2000 Antwerp, Belgium Steven.Latre@imec.be"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"2023110721555435800_bib1","article-title":"A public domain dataset for human activity recognition using smartphones","volume-title":"Proceedings of the 21st European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning","author":"Anguita","year":"2013"},{"key":"2023110721555435800_bib2","article-title":"Hypervector design for efficient hyperdimensional computing on edge devices","author":"Basaklar","year":"2021","journal-title":"Proceedings of the Tiny ML Research Symposium"},{"key":"2023110721555435800_bib3","first-page":"2125","article-title":"Adaptive prototype learning algorithms: Theoretical and experimental studies","volume":"7","author":"Chang","year":"2006","journal-title":"Journal of Machine Learning Research"},{"key":"2023110721555435800_bib4","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS50750.2020.9195216","article-title":"Dynamic hyperdimensional computing for improving accuracy-energy efficiency trade-offs","volume-title":"Proceedings of the IEEE Workshop on Signal Processing Systems, SiPS: Design and Implementation","author":"Chuang","year":"2020"},{"key":"2023110721555435800_bib5","author":"Dua","year":"2019","journal-title":"UCI machine learning repository"},{"key":"2023110721555435800_bib6","article-title":"LEHDC: Learning-based hyperdimensional computing classifier","author":"Duan","year":"2022","journal-title":"Proceedings of the Design Automation Conference"},{"key":"2023110721555435800_bib7","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 Circuits and Systems Magazine"},{"key":"2023110721555435800_bib8","article-title":"OnlineHD: Robust, efficient, and single-pass online learning using hyperdimensional system","author":"Hern\u00e1ndez-Cano","year":"2021","journal-title":"Proceedings of the Design, Automation and Test in Europe Conference and Exhibition"},{"key":"2023110721555435800_bib9","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.00885","article-title":"Constrained few-shot class-incremental learning","volume-title":"Proceedings of the Conference on Computer Vision and Pattern Recognition","author":"Hersche","year":"2022"},{"key":"2023110721555435800_bib10","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1007\/978-3-030-79150-662","article-title":"Hyperdimensional computing with learnable projection for user adaptation framework","author":"Hsiao","year":"2021","journal-title":"IFIP International Conference on Artificial Intelligence Applications and Innovations"},{"key":"2023110721555435800_bib11","first-page":"1","article-title":"VoiceHD: Hyperdimensional computing for efficient speech recognition","volume-title":"Proceedings of the IEEE International Conference on Rebooting Computing","author":"Imani","year":"2017"},{"key":"2023110721555435800_bib12","first-page":"1","article-title":"AdaptHD: Adaptive efficient training for brain-inspired hyperdimensional computing","volume-title":"Proceedings of the IEEE Biomedical Circuits and Systems Conference","author":"Imani","year":"2019"},{"issue":"1","key":"2023110721555435800_bib13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00521-021-05746-9","article-title":"Zero-shot classification with unseen prototype learning","volume":"35","author":"Ji","year":"2021","journal-title":"Neural Computing and Applications"},{"key":"2023110721555435800_bib14","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":"Cognitive Computation"},{"key":"2023110721555435800_bib15","doi-asserted-by":"publisher","DOI":"10.1145\/3277593.3277617","article-title":"Efficient human activity recognition using hyperdimensional computing","author":"Kim","year":"2018","journal-title":"Proceedings of the Eighth International Conference on the Internet of Things"},{"key":"2023110721555435800_bib16","doi-asserted-by":"publisher","first-page":"1053","DOI":"10.1109\/ISBI.2017.7950697","article-title":"Modality classification of medical images with distributed representations based on cellular automata reservoir computing","volume-title":"Proceedings of the International Symposium on Biomedical Imaging","author":"Kleyko","year":"2017"},{"issue":"6","key":"2023110721555435800_bib17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3538531","article-title":"A survey on hyperdimensional computing aka vector symbolic architectures, Part I: Models and data transformations","volume":"55","author":"Kleyko","year":"2022","journal-title":"ACM Computing Surveys"},{"key":"2023110721555435800_bib18","doi-asserted-by":"publisher","first-page":"5880","DOI":"10.1109\/TNNLS.2018","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 Transactions on Neural Networks and Learning Systems"},{"issue":"4","key":"2023110721555435800_bib19","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1561\/2200000019","volume":"5","author":"Kulis","year":"2013","journal-title":"Foundations in Trends in Machine Learning"},{"key":"2023110721555435800_bib20","doi-asserted-by":"crossref","DOI":"10.1109\/ISMAC.2019.8836136","article-title":"Performance analysis of hyperdimensional computing for character recognition","volume-title":"Proceedings of the International Symposium on Multimedia and Communication Technology","author":"Manabat","year":"2019"},{"key":"2023110721555435800_bib21","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1038\/s41928-020-00510-8","article-title":"A wearable biosensing system with in-sensor adaptive machine learning for hand gesture recognition","volume":"4","author":"Moin","year":"2021","journal-title":"Nature Electronics"},{"key":"2023110721555435800_bib22","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/s13218-019-00623-z","article-title":"An introduction to hyperdimensional computing for robotics","volume":"33","author":"Neubert","year":"2019","journal-title":"KI\u2014Kunstliche Intelligenz"},{"key":"2023110721555435800_bib23","first-page":"270","article-title":"Linear classifiers based on binary distributed representations","volume":"14","author":"Rachkovskij","year":"2007","journal-title":"Information Theories and Applications"},{"key":"2023110721555435800_bib24","doi-asserted-by":"crossref","DOI":"10.1109\/ICRC.2016.7738683","article-title":"Hyperdimensional biosignal processing: A case study for EMG-based hand gesture recognition","volume-title":"Proceedings of the IEEE International Conference of Rebooting Computing","author":"Rahimi","year":"2016"},{"key":"2023110721555435800_bib25","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1109\/JPROC.2018.2871163","article-title":"Efficient biosignal processing using hyperdimensional computing: Network templates for combined learning and classification of ExG signals","volume":"107","author":"Rahimi","year":"2019","journal-title":"Proceedings of the IEEE"},{"key":"2023110721555435800_bib26","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1145\/2934583.2934624","article-title":"A robust and energy-efficient classifier using brain-inspired hyperdimensional computing","volume-title":"Proceedings of the International Symposium on Low Power Electronics and Design","author":"Rahimi","year":"2016"},{"key":"2023110721555435800_bib27","article-title":"HDC-miniROCKET: Explicit time encoding in time series classification with hyperdimensional computing","author":"Schlegel","year":"2022","journal-title":"Proceedings of the International Joint Conference on Neural Networks"},{"key":"2023110721555435800_bib28","doi-asserted-by":"publisher","first-page":"3970","DOI":"10.1109\/EMBC46164.2021.9630898","article-title":"Detecting covid-19 related pneumonia on CT scans using hyperdimensional computing","volume-title":"Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society","author":"Watkinson","year":"2021"},{"key":"2023110721555435800_bib29","first-page":"207","article-title":"Distance metric learning for large margin nearest neighbor classification","volume":"10","author":"Weinberger","year":"2009","journal-title":"Journal of Machine Learning Research"},{"key":"2023110721555435800_bib30","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1093\/jigpal\/jzu028","article-title":"Reasoning with vectors: A continuous model for fast robust inference","volume":"23","author":"Widdows","year":"2015","journal-title":"Logic Journal of the IGPL"},{"key":"2023110721555435800_bib31","article-title":"Memory-efficient, limb position\u2013aware hand gesture recognition using hyperdimensional computing","author":"Zhou","year":"2021","journal-title":"Proceedings of the TinyML Research Symposium"},{"key":"2023110721555435800_bib32","first-page":"850","article-title":"ManiHD: Efficient hyper-dimensional learning using manifold trainable encoder","volume-title":"Proceedings of the Design, Automation and Test in Europe Conference and Exhibition","author":"Zou","year":"2021"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/35\/12\/2006\/2168808\/neco_a_01618.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/35\/12\/2006\/2168808\/neco_a_01618.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T16:56:22Z","timestamp":1699376182000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/35\/12\/2006\/117835\/Training-a-Hyperdimensional-Computing-Classifier"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"references-count":32,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,11,7]]},"published-print":{"date-parts":[[2023,11,7]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01618","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,12]]},"published":{"date-parts":[[2023,11,7]]}}}