{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:21:48Z","timestamp":1781587308927,"version":"3.54.5"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T00:00:00Z","timestamp":1684108800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T00:00:00Z","timestamp":1684108800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["SFRH\/BD\/144560\/2019"],"award-info":[{"award-number":["SFRH\/BD\/144560\/2019"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UIDB\/50021\/2020"],"award-info":[{"award-number":["UIDB\/50021\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Biol Cybern"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Interest in unsupervised learning architectures has been rising. Besides being biologically unnatural, it is costly to depend on large labeled data sets to get a well-performing classification system. Therefore, both the deep learning community and the more biologically-inspired models community have focused on proposing unsupervised techniques that can produce adequate hidden representations which can then be fed to a simpler supervised classifier. Despite great success with this approach, an ultimate dependence on a supervised model remains, which forces the number of classes to be known beforehand, and makes the system depend on labels to extract concepts. To overcome this limitation, recent work has been proposed that shows how a self-organizing map (SOM) can be used as a completely unsupervised classifier. However, to achieve success it required deep learning techniques to generate high quality embeddings. The purpose of this work is to show that we can use our previously proposed What-Where encoder in tandem with the SOM to get an end-to-end unsupervised system that is Hebbian. Such system, requires no labels to train nor does it require knowledge of which classes exist beforehand. It can be trained online and adapt to new classes that may emerge. As in the original work, we use the MNIST data set to run an experimental analysis and verify that the system achieves similar accuracies to the best ones reported thus far. Furthermore, we extend the analysis to the more difficult Fashion-MNIST problem and conclude that the system still performs.<\/jats:p>","DOI":"10.1007\/s00422-023-00963-y","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T18:02:28Z","timestamp":1684173748000},"page":"211-220","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Self-organizing maps on \u201cwhat-where\u201d codes towards fully unsupervised classification"],"prefix":"10.1007","volume":"117","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9775-5079","authenticated-orcid":false,"given":"Luis","family":"Sa-Couto","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andreas","family":"Wichert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,5,15]]},"reference":[{"key":"963_CR1","unstructured":"Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin. http:\/\/www.library.wisc.edu\/selectedtocs\/bg0137.pdf"},{"key":"963_CR2","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1016\/j.neunet.2009.09.004","volume":"23","author":"\u00c2 Cardoso","year":"2010","unstructured":"Cardoso \u00c2, Wichert A (2010) Neocognitron and the map transformation cascade. Neural Netw 23:74\u201388. https:\/\/doi.org\/10.1016\/j.neunet.2009.09.004","journal-title":"Neural Netw"},{"key":"963_CR3","volume-title":"Deep learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT press, Cambridge"},{"issue":"5656","key":"963_CR4","doi-asserted-by":"publisher","first-page":"814","DOI":"10.1038\/272814a0","volume":"272","author":"L Harkness","year":"1978","unstructured":"Harkness L, Bennet-Clark H (1978) The deep fovea as a focus indicator. Nature 272(5656):814\u2013816. https:\/\/doi.org\/10.1038\/272814a0","journal-title":"Nature"},{"key":"963_CR5","volume-title":"Neural networks and learning machines","author":"S Haykin","year":"2008","unstructured":"Haykin S (2008) Neural networks and learning machines. Pearson, London"},{"key":"963_CR6","volume-title":"Introduction to the theory of neural computation","author":"J Hertz","year":"1991","unstructured":"Hertz J, Krogh A, Palmer RG (1991) Introduction to the theory of neural computation. CRC Press, Boca Raton"},{"key":"963_CR7","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.neunet.2019.06.001","volume":"118","author":"B Illing","year":"2019","unstructured":"Illing B, Gerstner W, Brea J (2019) Biologically plausible deep learning\u2013but how far can we go with shallow networks? Neural Netw 118:90\u2013101. https:\/\/doi.org\/10.1016\/j.neunet.2019.06.001","journal-title":"Neural Netw"},{"key":"963_CR8","doi-asserted-by":"publisher","unstructured":"Khacef L, Miramond B, Barrientos D, Upegui A (2019) Self-organizing neurons: toward brain-inspired unsupervised learning. In: International Joint Conference on Neural Networks (IJCNN), pp 1\u20139. https:\/\/doi.org\/10.1109\/IJCNN.2019.8852098. IEEE","DOI":"10.1109\/IJCNN.2019.8852098"},{"key":"963_CR9","doi-asserted-by":"publisher","unstructured":"Khacef L, Rodriguez L, Miramond B (2020) Improving self-organizing maps with unsupervised feature extraction. In: International Conference on Neural Information Processing (ICONIP), pp 474\u2013486. https:\/\/doi.org\/10.1007\/978-3-030-63833-7_40","DOI":"10.1007\/978-3-030-63833-7_40"},{"key":"963_CR10","volume-title":"Self-organization and associative memory","author":"T Kohonen","year":"1984","unstructured":"Kohonen T (1984) Self-organization and associative memory. Springer, Berlin"},{"issue":"9","key":"963_CR11","doi-asserted-by":"publisher","first-page":"1464","DOI":"10.1109\/5.58325","volume":"78","author":"T Kohonen","year":"1990","unstructured":"Kohonen T (1990) The self-organizing map. Proc IEEE 78(9):1464\u20131480. https:\/\/doi.org\/10.1109\/5.58325","journal-title":"Proc IEEE"},{"issue":"16","key":"963_CR12","doi-asserted-by":"publisher","first-page":"7723","DOI":"10.1073\/pnas.1820458116","volume":"116","author":"D Krotov","year":"2019","unstructured":"Krotov D, Hopfield JJ (2019) Unsupervised learning by competing hidden units. Proc Natl Acad Sci 116(16):7723\u20137731. https:\/\/doi.org\/10.1073\/pnas.1820458116","journal-title":"Proc Natl Acad Sci"},{"key":"963_CR13","doi-asserted-by":"publisher","unstructured":"LeCun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, vol 86, pp 2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","DOI":"10.1109\/5.726791"},{"key":"963_CR14","unstructured":"LeCun Y, Cortes C, Burges C. MNIST handwritten digit database. http:\/\/yann.lecun.com\/exdb\/mnist\/ Accessed 12 Apr 2020"},{"key":"963_CR15","doi-asserted-by":"publisher","unstructured":"Le-Khac PH, Healy G, Smeaton AF (2020) Contrastive representation learning: a framework and review. IEEE Access 8:193907\u2013193934. https:\/\/doi.org\/10.1109\/ACCESS.2020.3031549","DOI":"10.1109\/ACCESS.2020.3031549"},{"issue":"1","key":"963_CR16","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1016\/S1364-6613(99)01418-7","volume":"4","author":"SP Liversedge","year":"2000","unstructured":"Liversedge SP, Findlay JM (2000) Saccadic eye movements and cognition. Trends Cogn Sci 4(1):6\u201314. https:\/\/doi.org\/10.1016\/S1364-6613(99)01418-7","journal-title":"Trends Cogn Sci"},{"key":"963_CR17","doi-asserted-by":"publisher","unstructured":"Lloyd S (1982) Least squares quantization in pcm. IEEE Trans Inf Theory 28(2):129\u2013137. https:\/\/doi.org\/10.1109\/TIT.1982.1056489","DOI":"10.1109\/TIT.1982.1056489"},{"key":"963_CR18","volume-title":"Vision: a computational investigation into the human representation and processing of visual information","author":"D Marr","year":"1982","unstructured":"Marr D (1982) Vision: a computational investigation into the human representation and processing of visual information. MIT press, Cambridge"},{"key":"963_CR19","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.spl.2013.09.026","volume":"84","author":"I Melnykov","year":"2014","unstructured":"Melnykov I, Melnykov V (2014) On k-means algorithm with the use of mahalanobis distances. Stat Probab Lett 84:88\u201395. https:\/\/doi.org\/10.1016\/j.spl.2013.09.026","journal-title":"Stat Probab Lett"},{"key":"963_CR20","volume-title":"Machine learning: a probabilistic perspective","author":"KP Murphy","year":"2012","unstructured":"Murphy KP (2012) Machine learning: a probabilistic perspective. MIT press, Cambridge"},{"key":"963_CR21","doi-asserted-by":"publisher","unstructured":"Ravichandran NB, Lansner A, Herman P (2020) Learning representations in bayesian confidence propagation neural networks. In: International Joint Conference on Neural Networks (IJCNN), pp 1\u20137. https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9207061","DOI":"10.1109\/IJCNN48605.2020.9207061"},{"key":"963_CR22","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1016\/S0364-0213(85)80010-0","volume":"9","author":"DE Rumelhart","year":"1985","unstructured":"Rumelhart DE, Zipser D (1985) Feature discovery by competitive learning. Cogn Sci 9:75\u2013112. https:\/\/doi.org\/10.1016\/S0364-0213(85)80010-0","journal-title":"Cogn Sci"},{"key":"963_CR23","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/j.neunet.2019.01.018","volume":"114","author":"L Sa-Couto","year":"2019","unstructured":"Sa-Couto L, Wichert A (2019) Attention inspired network: steep learning curve in an invariant pattern recognition model. Neural Netw 114:38\u201346. https:\/\/doi.org\/10.1016\/j.neunet.2019.01.018","journal-title":"Neural Netw"},{"key":"963_CR24","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1162\/neco_a_01243","volume":"32","author":"L Sa-Couto","year":"2020","unstructured":"Sa-Couto L, Wichert A (2020) Storing object-dependent sparse codes in a willshaw associative network. Neural Comput 32:136\u2013152. https:\/\/doi.org\/10.1162\/neco_a_01243","journal-title":"Neural Comput"},{"issue":"12","key":"963_CR25","doi-asserted-by":"publisher","first-page":"3334","DOI":"10.1162\/neco_a_01446","volume":"33","author":"L Sa-Couto","year":"2021","unstructured":"Sa-Couto L, Wichert A (2021) Simple convolutional-based models: Are they learning the task or the data? Neural Comput 33(12):3334\u20133350. https:\/\/doi.org\/10.1162\/neco_a_01446","journal-title":"Neural Comput"},{"issue":"8","key":"963_CR26","doi-asserted-by":"publisher","first-page":"6207","DOI":"10.1007\/s00521-021-06759-0","volume":"34","author":"L Sa-Couto","year":"2022","unstructured":"Sa-Couto L, Wichert A (2022) \u201cwhat-where\u2019\u2019 sparse distributed invariant representations of visual patterns. Neural Comput Appl 34(8):6207\u20136214. https:\/\/doi.org\/10.1007\/s00521-021-06759-0","journal-title":"Neural Comput Appl"},{"key":"963_CR27","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.neucom.2022.04.130","volume":"495","author":"L Sa-Couto","year":"2022","unstructured":"Sa-Couto L, Wichert A (2022) Using brain inspired principles to unsupervisedly learn good representations for visual pattern recognition. Neurocomputing 495:97\u2013104. https:\/\/doi.org\/10.1016\/j.neucom.2022.04.130","journal-title":"Neurocomputing"},{"key":"963_CR28","doi-asserted-by":"publisher","unstructured":"Sculley D (2010) Web-scale k-means clustering. In: 19th International Conference on World Wide Web, pp. 1177\u20131178. https:\/\/doi.org\/10.1145\/1772690.1772862","DOI":"10.1145\/1772690.1772862"},{"key":"963_CR29","doi-asserted-by":"crossref","unstructured":"Trappenberg T (2009) Fundamentals of computational neuroscience. OUP, Oxford","DOI":"10.1093\/oso\/9780199568413.001.0001"},{"key":"963_CR30","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms"}],"container-title":["Biological Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-023-00963-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00422-023-00963-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-023-00963-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T00:09:28Z","timestamp":1702426168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00422-023-00963-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,15]]},"references-count":30,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,6]]}},"alternative-id":["963"],"URL":"https:\/\/doi.org\/10.1007\/s00422-023-00963-y","relation":{},"ISSN":["1432-0770"],"issn-type":[{"value":"1432-0770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,15]]},"assertion":[{"value":"15 September 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 April 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflicts of interest. Code and data for all the experiments can be obtained by email request to the first author. All authors contributed equally. Finally, the first author is immensely grateful to Margarida for her comments and support throughout the whole process.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}