{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:58:12Z","timestamp":1780955892952,"version":"3.54.1"},"reference-count":35,"publisher":"MIT Press","issue":"7","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>We model human and animal learning by computing with high-dimensional vectors (e.g., D = 10,000). The architecture resembles traditional (von Neumann) computing with numbers, but the instructions refer to vectors and operate on them in superposition. The architecture includes a high-capacity memory for vectors, counterpart of the random-access memory (RAM) for numbers. The model\u2019s ability to learn from data reminds us of deep learning, but with an architecture closer to biology. The architecture agrees with an idea from psychology that human memory and learning involve a short-term working memory and a long-term data store. Neuroscience provides us with a model of the long-term memory, namely, the cortex of the cerebellum. With roots in psychology, biology, and traditional computing, a theory of computing with vectors can help us understand how brains compute. Application to learning by robots seems inevitable, but there is likely to be more, including language. Ultimately we want to compute with no more material and energy than brains use. To that end, we need a mathematical theory that agrees with psychology and biology and is suitable for nano-technology. We also need to exercise the theory in large-scale experiments. The analogy with traditional computing suggests that the architecture be programmable in terms of variables, values, and data structures, the very things that have made traditional computing ubiquitous and that seem worth learning from and emulating.<\/jats:p>","DOI":"10.1162\/neco.a.1523","type":"journal-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:52:11Z","timestamp":1777398731000},"page":"1117-1134","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":0,"title":["Autonomous Learning With High-Dimensional Computing Architecture Similar to Von Neumann\u2019s"],"prefix":"10.1162","volume":"38","author":[{"given":"Pentti","family":"Kanerva","sequence":"first","affiliation":[{"name":"Redwood Center for Theoretical Neuroscience, University of California at Berkeley, Berkeley, CA 94720-3198, USA pkanerva@berkeley.edu"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","published-online":{"date-parts":[[2026,6,2]]},"reference":[{"key":"2026060817054815100_bib1","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/0025-5564(71)90051-4","article-title":"A theory of cerebellar functions","volume":"10","author":"Albus,","year":"1971","journal-title":"Mathematical Biosciences"},{"key":"2026060817054815100_bib2","volume-title":"Brains, behavior, and bobotics","author":"Albus","year":"1981"},{"key":"2026060817054815100_bib3","volume-title":"Human associative memory.","author":"Anderson","year":"1973"},{"key":"2026060817054815100_bib4","first-page":"89","article-title":"Human memory: A proposed system and its control processes","volume-title":"The psychology of learning and motivation: Advances in research and theory","author":"Atkinson","year":"1968"},{"key":"2026060817054815100_bib5","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-662-13147-3","volume-title":"The cerebellum as a neuronal machine","author":"Eccles","year":"1967"},{"issue":"6","key":"2026060817054815100_bib6","doi-asserted-by":"publisher","first-page":"1449","DOI":"10.1162\/neco_a_01084","article-title":"A theory of sequence indexing and working memory in recurrent neural networks","volume":"30","author":"Frady","year":"2018","journal-title":"Neural Computation"},{"issue":"4","key":"2026060817054815100_bib7","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1016\/s1364-6613(99)01294-2","article-title":"Catastrophic forgetting in connectionist networks","volume":"3","author":"French","year":"1999","journal-title":"Trends in Cognitive Science"},{"issue":"8","key":"2026060817054815100_bib8","doi-asserted-by":"publisher","first-page":"2038","DOI":"10.1162\/NECO_a_00467","article-title":"Representing objects, relations, and sequences","volume":"25","author":"Gallant","year":"2013","journal-title":"Neural Computation"},{"key":"2026060817054815100_bib9","first-page":"133","article-title":"Vector symbolic architectures answer Jackendoff\u2019s challenges for cognitive neuroscience","volume-title":"Proceedings of the Joint International Conference on Cognitive Science","author":"Gayler","year":"2003"},{"key":"2026060817054815100_bib10","volume-title":"Parallel models of associative memory","author":"Hinton","year":"1981"},{"key":"2026060817054815100_bib11","author":"Huang","year":"2022","journal-title":"Computing with hypervectors for efficient speaker identification."},{"key":"2026060817054815100_bib12","author":"Jaeckel","year":"1989","journal-title":"A class of designs for a sparse distributed memory"},{"key":"2026060817054815100_bib13","author":"James","year":"1890"},{"key":"2026060817054815100_bib14","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1007\/978-3-319-52289-0_21","article-title":"Language geometry using random indexing","volume-title":"Quantum Interaction: Proceedings of the 10th International Conference","author":"Joshi","year":"2017"},{"key":"2026060817054815100_bib15","volume-title":"Sparse distributed memory.","author":"Kanerva","year":"1988"},{"key":"2026060817054815100_bib16","first-page":"50","article-title":"Sparse distributed memory and related models","volume-title":"Associative neural memories: Theory and implementation","author":"Kanerva","year":"1993"},{"issue":"2","key":"2026060817054815100_bib17","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":"2026060817054815100_bib18","first-page":"25","article-title":"Hyperdimensional computing: An algebra for computing with vectors","volume-title":"Advances in semiconductor technologies: Selected topics beyond conventional CMOS","author":"Kanerva","year":"2023"},{"key":"2026060817054815100_bib19","article-title":"Random indexing of text samples for latent semantic analysis","volume-title":"Proceedings of the 22nd Annual Meeting of the Cognitive Science Society","author":"Kanerva","year":"2000"},{"issue":"10","key":"2026060817054815100_bib20","doi-asserted-by":"publisher","first-page":"1538","DOI":"10.1109\/JPROC.2022.3209104","article-title":"Vector symbolic architectures as a computing framework for emerging hardware","volume":"110","author":"Kleyko","year":"2022","journal-title":"Proceedings of the IEEE"},{"key":"2026060817054815100_bib21","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1007\/BF00187293","article-title":"Changes in volume, surface estimate, three-dimensional shape and total number of neurons of the human primary visual cortex from midgestation until old age","volume":"190","author":"Leuba","year":"1994","journal-title":"Anatomy and Embryology"},{"key":"2026060817054815100_bib22","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1093\/acprof:oso\/9780195159561.003.0007","article-title":"Cerebellum","volume-title":"The synaptic organization of the brain","author":"Llin\u00e1s","year":"2004"},{"key":"2026060817054815100_bib23","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1113\/jphysiol.1969.sp008820","article-title":"A theory of cerebellar cortex","volume":"202","author":"Marr","year":"1969","journal-title":"Journal of Physiology"},{"issue":"2","key":"2026060817054815100_bib24","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1037\/h0043158","article-title":"The magical number seven, plus or minus two: Some limits on our capacity for processing information","volume":"63","author":"Miller","year":"1956","journal-title":"Psychological Review"},{"issue":"9","key":"2026060817054815100_bib25","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1016\/j.tics.2024.06.011","article-title":"Why concepts are (probably) vectors","volume":"28","author":"Piantadosi","year":"2024","journal-title":"Trends in Cognitive Sciences"},{"key":"2026060817054815100_bib26","first-page":"30","article-title":"Holographic reduced representations: Convolution algebra for compositional distributed representations","volume-title":"Proceedings of the 12th International Joint Conference on Artificial Intelligence","author":"Plate","year":"1991"},{"key":"2026060817054815100_bib27","volume-title":"Holographic reduced representation: Distributed representation of cognitive structure.","author":"Plate","year":"2003"},{"issue":"2","key":"2026060817054815100_bib28","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1037\/0033-295X.88.2.93","article-title":"Search of associative memory","volume":"88","author":"Raaijmakers","year":"1981","journal-title":"Psychological Review"},{"key":"2026060817054815100_bib29","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780195159561.001.1","volume-title":"The synaptic organization of the brain","author":"Shepherd","year":"2004","edition":"5th"},{"key":"2026060817054815100_bib30","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1093\/acprof:oso\/9780195159561.003.0006","article-title":"Retina","volume-title":"The synaptic organization of the brain","author":"Sterling","year":"2004","edition":"5th"},{"key":"2026060817054815100_bib31","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2022.867568","article-title":"On separating long- and short-term memories in hyperdimensional computing","author":"Teeters","year":"2023","journal-title":"Frontiers in Neuroscience"},{"key":"2026060817054815100_bib32","first-page":"65","article-title":"Hey Pentti, we did it!: A fully vector-symbolic Lisp","author":"Tomkins-Flanagan","year":"2024","journal-title":"Proceedings of the 22nd International Conference on Cognitive Modeling"},{"key":"2026060817054815100_bib33","volume-title":"Organization of memory.","author":"Tulving","year":"1972"},{"issue":"5","key":"2026060817054815100_bib34","doi-asserted-by":"publisher","first-page":"352","DOI":"10.1037\/h0020071","article-title":"Encoding specificity and retrieval processes in episodic memory","volume":"80","author":"Tulving","year":"1973","journal-title":"Psychological Review"},{"key":"2026060817054815100_bib35","author":"Yang","year":"2023","journal-title":"Cognitive modeling and learning with sparse binary hypervectors."}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/38\/7\/1117\/2596782\/neco.a.1523.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/38\/7\/1117\/2596782\/neco.a.1523.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T21:05:57Z","timestamp":1780952757000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/38\/7\/1117\/136442\/Autonomous-Learning-With-High-Dimensional"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,2]]},"references-count":35,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,6,2]]},"published-print":{"date-parts":[[2026,6,2]]}},"URL":"https:\/\/doi.org\/10.1162\/neco.a.1523","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,7]]},"published":{"date-parts":[[2026,6,2]]}}}