{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T15:32:47Z","timestamp":1780673567376,"version":"3.54.1"},"reference-count":47,"publisher":"MIT Press - Journals","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2020,12]]},"abstract":"<jats:p> The ability to encode and manipulate data structures with distributed neural representations could qualitatively enhance the capabilities of traditional neural networks by supporting rule-based symbolic reasoning, a central property of cognition. Here we show how this may be accomplished within the framework of Vector Symbolic Architectures (VSAs) (Plate, 1991 ; Gayler, 1998 ; Kanerva, 1996 ), whereby data structures are encoded by combining high-dimensional vectors with operations that together form an algebra on the space of distributed representations. In particular, we propose an efficient solution to a hard combinatorial search problem that arises when decoding elements of a VSA data structure: the factorization of products of multiple codevectors. Our proposed algorithm, called a resonator network, is a new type of recurrent neural network that interleaves VSA multiplication operations and pattern completion. We show in two examples\u2014parsing of a tree-like data structure and parsing of a visual scene\u2014how the factorization problem arises and how the resonator network can solve it. More broadly, resonator networks open the possibility of applying VSAs to myriad artificial intelligence problems in real-world domains. The companion article in this issue (Kent, Frady, Sommer, &amp; Olshausen, 2020 ) presents a rigorous analysis and evaluation of the performance of resonator networks, showing it outperforms alternative approaches. <\/jats:p>","DOI":"10.1162\/neco_a_01331","type":"journal-article","created":{"date-parts":[[2020,10,20]],"date-time":"2020-10-20T21:25:44Z","timestamp":1603229144000},"page":"2311-2331","source":"Crossref","is-referenced-by-count":43,"title":["Resonator Networks, 1: An Efficient Solution for Factoring High-Dimensional, Distributed Representations of Data Structures"],"prefix":"10.1162","volume":"32","author":[{"given":"E. Paxon","family":"Frady","sequence":"first","affiliation":[{"name":"Redwood Center for Theoretical Neuroscience, University of California, Berkeley, Berkeley, CA 94720, U.S.A., and Intel Laboratories, Neuromorphic Computing Lab, San Francisco, CA, 94111, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Spencer J.","family":"Kent","sequence":"additional","affiliation":[{"name":"Redwood Center for Theoretical Neuroscience and Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA 94720, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bruno A.","family":"Olshausen","sequence":"additional","affiliation":[{"name":"Redwood Center for Theoretical Neuroscience, Helen Wills Neuroscience Institute, and School of Optometry, University of California, Berkeley, Berkeley, CA 94720, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Friedrich T.","family":"Sommer","sequence":"additional","affiliation":[{"name":"Redwood Center for Theoretical Neuroscience and Helen Wills Neuroscience Institute, University of California, Berkeley, Berkeley, CA 94720, U.S.A., and Intel Laboratories, Neuromorphic Computing Lab, San Francisco, CA 94111, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511984037.014"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1167\/jov.20.7.34"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2377712"},{"key":"B4","first-page":"3","volume":"2","author":"Barrow H.","year":"1978","journal-title":"Computer Vision Systems"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00247"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3758\/s13428-011-0125-5"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178714"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1007\/s11571-012-9219-8"},{"key":"B10","volume-title":"The language of thought","author":"Fodor J. A.","year":"1975"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0277(88)90031-5"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01084"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1902653116"},{"key":"B15","volume-title":"Advances in analogy research: Integration of theory and data from the cognitive, computational, and neural sciences","author":"Gayler R. W.","year":"1998"},{"key":"B16","volume-title":"Proceedings of the ICCS\/ASCS International Conference on Cognitive Science","author":"Gayler R.","year":"2003"},{"key":"B17","first-page":"165","volume-title":"New Frontiers in Analogy Research: Proceedings of the Second International Analogy Conference-Analogy","volume":"9","author":"Gayler R. W.","year":"2009"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(90)90004-J"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.104.3.427"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1093\/acprof:oso\/9780198270126.001.0001"},{"key":"B22","unstructured":"Joshi, A., Halseth, J. T. & Kanerva, P. (2016). Language geometry using random indexing. In Proceedings of the International Symposium on Quantum Interaction (pp. 265\u2013274). Berlin: Springer."},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-61510-5_146"},{"key":"B24","first-page":"358","volume-title":"Proceedings of the 1997 Real World Computing Symposium","author":"Kanerva P.","year":"1997"},{"key":"B25","first-page":"194","volume-title":"Proceedings of the International Workshop on Hybrid Neural Systems","author":"Kanerva P.","year":"1998"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-009-9009-8"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1162\/neco_a_01329"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2814400"},{"key":"B29","unstructured":"Laiho, M., Poikonen, J. H., Kanerva, P. & Lehtonen, E. (2015). High-dimensional computing with sparse vectors. In Proceedings of the 2015 IEEE Biomedical Circuits and Systems Conference (pp. 1\u20134). Piscataway, NJ: IEEE."},{"key":"B31","volume-title":"The MNIST database of handwritten digits","author":"LeCun Y.","year":"1998"},{"key":"B32","volume-title":"The concentration of measure phenomenon","author":"Ledoux M.","year":"2001"},{"key":"B33","volume-title":"Parallel distributed processing: Explorations in the Microstructure of Cognition","author":"McClelland J. L.","year":"1986"},{"key":"B34","first-page":"474","volume-title":"Advances in neural information processing systems, 2","author":"Mel B. W.","year":"1990"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2010.01-09-953"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1037\/h0043158"},{"key":"B37","volume-title":"Proceedings of the 28th International Conference on Machine Learning","author":"Nickel M.","year":"2011"},{"key":"B38","first-page":"30","volume-title":"Proceedings of the International Joint Conference on Artificial Intelligence","author":"Plate T. A.","year":"1991"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1109\/72.377968"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1111\/1468-0394.00125"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.1088\/0954-898X_11_4_305"},{"key":"B42","volume-title":"Holographic reduced representation: Distributed representation of cognitive structure","author":"Plate T. A.","year":"2003"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1162\/089976601300014592"},{"key":"B44","volume-title":"Proceedings of the 37th Annual Meeting of the Cognitive Science Society.","author":"R\u00e4s\u00e4nen O. J.","year":"2015"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(90)90007-M"},{"key":"B46","first-page":"926","volume-title":"Advances in neural information processing systems","author":"Socher R.","year":"2013"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1016\/0010-0285(80)90005-5"},{"key":"B48","first-page":"5998","volume-title":"Advances in neural information processing systems","author":"Vaswani A.","year":"2017"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)80825-9"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(00)80818-1"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01331","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,3,12]],"date-time":"2021-03-12T21:43:53Z","timestamp":1615585433000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/32\/12\/2311-2331\/95651"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12]]},"references-count":47,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2020,12]]}},"alternative-id":["10.1162\/neco_a_01331"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01331","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12]]}}}