{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T23:46:47Z","timestamp":1767829607895,"version":"3.49.0"},"reference-count":43,"publisher":"Association for Computing Machinery (ACM)","issue":"6","license":[{"start":{"date-parts":[[2022,10,18]],"date-time":"2022-10-18T00:00:00Z","timestamp":1666051200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"CRISP, one of six centers in JUMP, an SRC program sponsored by DARPA, in part by SRC-Global Research Collaboration Grant","award":["2988.001"],"award-info":[{"award-number":["2988.001"]}]},{"name":"NSF","award":["1527034, 1730158, 1826967, 1911095, and 2003277"],"award-info":[{"award-number":["1527034, 1730158, 1826967, 1911095, and 2003277"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Embed. Comput. Syst."],"published-print":{"date-parts":[[2022,11,30]]},"abstract":"<jats:p>Today\u2019s systems rely on sending all the data to the cloud and then using complex algorithms, such as Deep Neural Networks, which require billions of parameters and many hours to train a model. In contrast, the human brain can do much of this learning effortlessly. Hyperdimensional (HD) Computing aims to mimic the behavior of the human brain by utilizing high-dimensional representations. This leads to various desirable properties that other Machine Learning (ML) algorithms lack, such as robustness to noise in the system and simple, highly parallel operations. In this article, we propose \ud835\udda7\ud835\uddd2\ud835\udda3\ud835\uddb1\ud835\udda4\ud835\udda0, a HyperDimensional Computing system that is Robust, Efficient, and Accurate. We propose a Processing-in-Memory (PIM) architecture that works in a federated learning environment with challenging communication scenarios that cause errors in the transmitted data. \ud835\udda7\ud835\uddd2\ud835\udda3\ud835\uddb1\ud835\udda4\ud835\udda0 adaptively changes the bitwidth of the model based on the signal-to-noise ratio (SNR) of the incoming sample to maintain the accuracy of the HD model while achieving significant speedup and energy efficiency. Our PIM architecture is able to achieve a speedup of 28\u00d7 and 255\u00d7 better energy efficiency compared to the baseline PIM architecture for Classification and achieves 32 \u00d7 speed up and 289 \u00d7 higher energy efficiency than the baseline architecture for Clustering. \ud835\udda7\ud835\uddd2\ud835\udda3\ud835\uddb1\ud835\udda4\ud835\udda0 is able to achieve this by relaxing hardware parameters to gain energy efficiency and speedup while introducing computational errors. We show experimentally, HD Computing is able to handle the errors without a significant drop in accuracy due to its unique robustness property. For wireless noise, we found that \ud835\udda7\ud835\uddd2\ud835\udda3\ud835\uddb1\ud835\udda4\ud835\udda0 is 48 \u00d7 more robust to noise than other comparable ML algorithms. Our results indicate that our proposed system loses less than 1% Classification accuracy, even in scenarios with an SNR of 6.64. We additionally test the robustness of using HD Computing for Clustering applications and found that our proposed system also looses less than 1% in the mutual information score, even in scenarios with an SNR under 7 dB, which is 57 \u00d7 more robust to noise than K-means.<\/jats:p>","DOI":"10.1145\/3524067","type":"journal-article","created":{"date-parts":[[2022,7,13]],"date-time":"2022-07-13T10:15:31Z","timestamp":1657707331000},"page":"1-25","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["\ud835\udda7\ud835\uddd2\ud835\udda3\ud835\uddb1\ud835\udda4\ud835\udda0: Utilizing Hyperdimensional Computing for a More Robust and Efficient Machine Learning System"],"prefix":"10.1145","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7921-2561","authenticated-orcid":false,"given":"Justin","family":"Morris","sequence":"first","affiliation":[{"name":"University of California San Diego, La Jolla, CA and San Diego State University, San Diego, CA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5092-5074","authenticated-orcid":false,"given":"Kazim","family":"Ergun","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, CA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3655-0501","authenticated-orcid":false,"given":"Behnam","family":"Khaleghi","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, CA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5761-0622","authenticated-orcid":false,"given":"Mohen","family":"Imani","sequence":"additional","affiliation":[{"name":"University of California Irvine, Irvine, CA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6347-9061","authenticated-orcid":false,"given":"Baris","family":"Aksanli","sequence":"additional","affiliation":[{"name":"San Diego State University, San Diego, CA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6954-997X","authenticated-orcid":false,"given":"Tajana","family":"Simunic","sequence":"additional","affiliation":[{"name":"University of California San Diego, La Jolla, CA"}]}],"member":"320","published-online":{"date-parts":[[2022,10,18]]},"reference":[{"key":"e_1_3_1_2_2","unstructured":"Jakub Kone\u010dn\u1ef3 H. Brendan McMahan Felix X. Yu Peter Richt\u00e1rik Ananda Theertha Suresh and Dave Bacon. 2016. Federated learning: Strategies for improving communication efficiency. Retrieved from https:\/\/arXiv:1610.05492."},{"key":"e_1_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-009-9009-8"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00028"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196060"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/3377930.3390226"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA.2017.28"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3289602.3293913"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3240765.3240811"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00039"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3391901"},{"key":"e_1_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3007787.3001139"},{"issue":"14","key":"e_1_3_1_13_2","first-page":"527","article-title":"Network simulations with the ns-3 simulator","volume":"14","author":"Henderson Thomas R.","year":"2008","unstructured":"Thomas R. Henderson, Mathieu Lacage, George F. Riley, Craig Dowell, and Joseph Kopena. 2008. Network simulations with the ns-3 simulator. SIGCOMM Demonst. 14, 14 (2008), 527.","journal-title":"SIGCOMM Demonst."},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2017.8123650"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3316781.3317785"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2016.7738683"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8715147"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714821"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9372119"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322237"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00011"},{"key":"e_1_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410463.3414634"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2871163"},{"key":"e_1_3_1_24_2","first-page":"64","volume-title":"Proceedings of the International Symposium on Low Power Electronics and Design","author":"Rahimi Abbas","year":"2016","unstructured":"Abbas Rahimi, Pentti Kanerva, and Jan M. Rabaey. 2016. A robust and energy-efficient classifier using brain-inspired hyperdimensional computing. In Proceedings of the International Symposium on Low Power Electronics and Design. ACM, 64\u201369."},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRC.2017.8123650"},{"key":"e_1_3_1_26_2","article-title":"QuantHD: A quantization framework for hyperdimensional computing","author":"Imani Mohsen","year":"2019","unstructured":"Mohsen Imani et\u00a0al. 2019. QuantHD: A quantization framework for hyperdimensional computing. IEEE Trans. Comput.-Aided Design Integr. Circ. Syst. 39, 10 (2019), 2268\u20132278.","journal-title":"IEEE Trans. Comput.-Aided Design Integr. Circ. Syst."},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM.2016.7838428"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2652320"},{"key":"e_1_3_1_29_2","unstructured":"Retrieved from https:\/\/standards.ieee.org\/standard\/802_11n-2009.html IEEE. 2009. 802.11n-2009\u2014IEEE Standard for Information technology\u2014Local and metropolitan area networks"},{"key":"e_1_3_1_30_2","unstructured":"Retrieved from https:\/\/standards.ieee.org\/standard\/802_15_4-2020.html IEEE. 2020. 802.15.4-2020\u2014IEEE Standard for Low-Rate Wireless Networks"},{"key":"e_1_3_1_31_2","volume-title":"Wireless Communications: Principles and Practice","author":"Rappaport Theodore S.","year":"1996","unstructured":"Theodore S. Rappaport et\u00a0al. 1996. Wireless Communications: Principles and Practice. Vol. 2. Prentice Hall PTR, New Jersey."},{"key":"e_1_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/VETECS.2000.851585"},{"key":"e_1_3_1_33_2","unstructured":"Retrieved from https:\/\/www.itu.int\/\/ International Telecommunication Union"},{"key":"e_1_3_1_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2952584"},{"key":"e_1_3_1_35_2","unstructured":"Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/Daily+and+Sports+Activities UCI Machine Learning Repository"},{"key":"e_1_3_1_36_2","unstructured":"Retrieved from https:\/\/archive.ics.uci.edu\/ml\/datasets\/cardiotocography UCI Machine Learning Repository"},{"key":"e_1_3_1_37_2","unstructured":"Gregory Griffin Alex Holub and Pietro Perona. 2007. Caltech-256 object category dataset. California Institute of Technology."},{"key":"e_1_3_1_38_2","unstructured":"http:\/\/archive.ics.uci.edu\/ml\/datasets\/ISOLET UCI Machine Learning Repository"},{"key":"e_1_3_1_39_2","first-page":"240","volume-title":"Proceedings of the Lernen, Wissensentdeckung und Adaptivit GI Workshops (LWA\u201905)","author":"Ultsch Alfred","year":"2005","unstructured":"Alfred Ultsch. 2005. U* C: Self-organized clustering with emergent feature maps. In Proceedings of the Lernen, Wissensentdeckung und Adaptivit GI Workshops (LWA\u201905). Citeseer, 240\u2013244."},{"key":"e_1_3_1_40_2","doi-asserted-by":"crossref","unstructured":"Saransh Gupta Justin Morris Mohsen Imani Ranganathan Ramkumar Jeffrey Yu Aniket Tiwari Baris Aksanli and Tajana \u0160imuni\u0107 Rosing. 2020. THRIFTY: Training with hyperdimensional computing across flash hierarchy.","DOI":"10.1145\/3400302.3415723"},{"key":"e_1_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/FCCM.2017.43"},{"key":"e_1_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218737"},{"key":"e_1_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2019.00076"},{"key":"e_1_3_1_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICT.2017.7998249"}],"container-title":["ACM Transactions on Embedded Computing Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524067","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524067","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3524067","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:31:04Z","timestamp":1750188664000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3524067"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,18]]},"references-count":43,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,11,30]]}},"alternative-id":["10.1145\/3524067"],"URL":"https:\/\/doi.org\/10.1145\/3524067","relation":{},"ISSN":["1539-9087","1558-3465"],"issn-type":[{"value":"1539-9087","type":"print"},{"value":"1558-3465","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,18]]},"assertion":[{"value":"2021-07-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-04","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-10-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}