{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:04:56Z","timestamp":1782965096398,"version":"3.54.5"},"reference-count":63,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T00:00:00Z","timestamp":1709769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T00:00:00Z","timestamp":1709769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000185","name":"United States Department of Defense | Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-024-00802-0","type":"journal-article","created":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:06:27Z","timestamp":1709809587000},"page":"271-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":37,"title":["Learning high-level visual representations from a child\u2019s perspective without strong inductive biases"],"prefix":"10.1038","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5486-7385","authenticated-orcid":false,"given":"A. Emin","family":"Orhan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8959-3401","authenticated-orcid":false,"given":"Brenden M.","family":"Lake","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,7]]},"reference":[{"key":"802_CR1","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1016\/0022-0965(83)90085-1","volume":"35","author":"P Bomba","year":"1983","unstructured":"Bomba, P. & Siqueland, E. The nature and structure of infant form categories. J. Exp. Child Psychol. 35, 294\u2013328 (1983).","journal-title":"J. Exp. Child Psychol."},{"key":"802_CR2","doi-asserted-by":"crossref","unstructured":"Murphy, G. The Big Book of Concepts (MIT, 2002).","DOI":"10.7551\/mitpress\/1602.001.0001"},{"key":"802_CR3","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/0010-0285(83)90017-8","volume":"15","author":"P Kellman","year":"1983","unstructured":"Kellman, P. & Spelke, E. Perception of partly occluded objects in infancy. Cogn. Psychol. 15, 483\u2013524 (1983).","journal-title":"Cogn. Psychol."},{"key":"802_CR4","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1037\/0033-295X.99.4.605","volume":"99","author":"E Spelke","year":"1992","unstructured":"Spelke, E., Breinlinger, K., Macomber, J. & Jacobson, K. Origin of knowledge. Psychol. Rev. 99, 605\u2013632 (1992).","journal-title":"Psychol. Rev."},{"key":"802_CR5","doi-asserted-by":"publisher","first-page":"310","DOI":"10.1167\/jov.20.11.310","volume":"20","author":"V Ayzenberg","year":"2020","unstructured":"Ayzenberg, V. & Lourenco, S. Young children outperform feed-forward and recurrent neural networks on challenging object recognition tasks. J. Vis. 20, 310\u2013310 (2020).","journal-title":"J. Vis."},{"key":"802_CR6","doi-asserted-by":"crossref","unstructured":"Huber, L. S., Geirhos, R. & Wichmann, F. A. The developmental trajectory of object recognition robustness: children are like small adults but unlike big deep neural networks. J. Vis. 23, 4 (2023).","DOI":"10.1167\/jov.23.7.4"},{"key":"802_CR7","unstructured":"Locke, J. An Essay Concerning Human Understanding (ed. Fraser, A. C.) (Clarendon Press, 1894)."},{"key":"802_CR8","doi-asserted-by":"crossref","unstructured":"Leibniz, G. New Essays on Human Understanding 2nd edn (eds Remnant, P. & Bennett, J.) (Cambridge Univ. Press, 1996).","DOI":"10.1017\/CBO9781139166874"},{"key":"802_CR9","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1016\/0010-0277(94)90039-6","volume":"50","author":"E Spelke","year":"1994","unstructured":"Spelke, E. Initial knowledge: six suggestions. Cognition 50, 431\u2013445 (1994).","journal-title":"Cognition"},{"key":"802_CR10","unstructured":"Markman, E. Categorization and Naming in Children (MIT, 1989)."},{"key":"802_CR11","doi-asserted-by":"crossref","unstructured":"Merriman, W., Bowman, L. & MacWhinney, B. The mutual exclusivity bias in children\u2019s word learning. Monogr. Soc. Res. Child Dev. 54, 1\u2013132 (1989).","DOI":"10.2307\/1166130"},{"key":"802_CR12","doi-asserted-by":"crossref","unstructured":"Elman, J., Bates, E. & Johnson, M. Rethinking Innateness: A Connectionist Perspective on Development (MIT, 1996).","DOI":"10.7551\/mitpress\/5929.001.0001"},{"key":"802_CR13","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1162\/opmi_a_00039","volume":"5","author":"J Sullivan","year":"2022","unstructured":"Sullivan, J., Mei, M., Perfors, A., Wojcik, E. & Frank, M. SAYCam: a large, longitudinal audiovisual dataset recorded from the infant\u2019s perspective. Open Mind 5, 20\u201329 (2022).","journal-title":"Open Mind"},{"key":"802_CR14","doi-asserted-by":"crossref","unstructured":"Caron, M. et al. Emerging properties in self-supervised vision transformers. In Proc. IEEE\/CVF International Conference on Computer Vision 9650\u20139660 (IEEE, 2021).","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"802_CR15","unstructured":"Zhou, P. et al. Mugs: a multi-granular self-supervised learning framework. Preprint at https:\/\/arxiv.org\/abs\/2203.14415 (2022)."},{"key":"802_CR16","doi-asserted-by":"crossref","unstructured":"He, K. et al. Masked autoencoders are scalable vision learners. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition 15979\u201315988 (IEEE, 2022).","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"802_CR17","unstructured":"Dosovitskiy, A. et al. An image is worth 16x16 words: transformers for image recognition at scale. In International Conference on Learning Representations (2020)."},{"key":"802_CR18","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P., Tu, Z. & He, K. Aggregated residual transformations for deep neural networks. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 1492\u20131500 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.634"},{"key":"802_CR19","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O. et al. ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211\u2013252 (2015).","journal-title":"Int. J. Comput. Vis."},{"key":"802_CR20","unstructured":"Smaira, L. et al. A short note on the Kinetics-700-2020 human action dataset. Preprint at https:\/\/arxiv.org\/abs\/2010.10864 (2020)."},{"key":"802_CR21","unstructured":"Grauman, K. et al. Ego4D: around the world in 3,000 hours of egocentric video. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 18995\u201319012 (IEEE, 2022)."},{"key":"802_CR22","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R. & Ommer, B. Taming transformers for high-resolution image synthesis. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition 12873\u201312883 (IEEE, 2021).","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"802_CR23","unstructured":"Radford, A. et al. Language models are unsupervised multitask learners. OpenAI https:\/\/cdn.openai.com\/better-language-models\/language_models_are_unsupervised_multitask_learners.pdf (2019)."},{"key":"802_CR24","doi-asserted-by":"crossref","unstructured":"Zhou, B., Khosla, A., Lapedriza, A., Oliva, A. & Torralba, A. Learning deep features for discriminative localization. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 2921\u20132929 (IEEE, 2016).","DOI":"10.1109\/CVPR.2016.319"},{"key":"802_CR25","unstructured":"van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)."},{"key":"802_CR26","doi-asserted-by":"crossref","unstructured":"Kuznetsova, A. et al. The Open Images Dataset V4. Int. J. Comput. Vis. 128, 1956\u20131981 (2020).","DOI":"10.1007\/s11263-020-01316-z"},{"key":"802_CR27","doi-asserted-by":"publisher","first-page":"2124","DOI":"10.3389\/fpsyg.2017.02124","volume":"8","author":"L Smith","year":"2017","unstructured":"Smith, L. & Slone, L. A developmental approach to machine learning? Front. Psychol. 8, 2124 (2017).","journal-title":"Front. Psychol."},{"key":"802_CR28","unstructured":"Bambach, S., Crandall, D., Smith, L. & Yu, C. Toddler-inspired visual object learning. Adv. Neural Inf. Process. Syst. 31, 1209\u20131218 (2018)."},{"key":"802_CR29","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1038\/s42256-022-00488-2","volume":"4","author":"L Zaadnoordijk","year":"2022","unstructured":"Zaadnoordijk, L., Besold, T. & Cusack, R. Lessons from infant learning for unsupervised machine learning. Nat. Mach. Intell. 4, 510\u2013520 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"802_CR30","first-page":"9960","volume":"33","author":"E Orhan","year":"2020","unstructured":"Orhan, E., Gupta, V. & Lake, B. Self-supervised learning through the eyes of a child. Adv. Neur. In. 33, 9960\u20139971 (2020).","journal-title":"Adv. Neur. In."},{"key":"802_CR31","unstructured":"Lee, D., Gujarathi, P. & Wood, J. Controlled-rearing studies of newborn chicks and deep neural networks. Preprint at https:\/\/arxiv.org\/abs\/2112.06106 (2021)."},{"key":"802_CR32","doi-asserted-by":"publisher","first-page":"e2014196118","DOI":"10.1073\/pnas.2014196118","volume":"118","author":"C Zhuang","year":"2021","unstructured":"Zhuang, C. et al. Unsupervised neural network models of the ventral visual stream. Proc. Natl Acad. Sci. USA 118, e2014196118 (2021).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"802_CR33","doi-asserted-by":"crossref","unstructured":"Zhuang, C. et al. How well do unsupervised learning algorithms model human real-time and life-long learning? In Thirty-sixth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2022).","DOI":"10.32470\/CCN.2022.1155-0"},{"key":"802_CR34","doi-asserted-by":"crossref","unstructured":"Vong, W. K., Wang, W., Orhan, A. E. & Lake, B. M. Grounded language acquisition through the eyes and ears of a single child. Science 383, 504\u2013511 (2024).","DOI":"10.1126\/science.adi1374"},{"key":"802_CR35","first-page":"11525","volume":"33","author":"F Locatello","year":"2020","unstructured":"Locatello, F. et al. Object-centric learning with slot attention. Adv. Neur. In. 33, 11525\u201311538 (2020).","journal-title":"Adv. Neur. In."},{"key":"802_CR36","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/s41583-020-0277-3","volume":"21","author":"T Lillicrap","year":"2020","unstructured":"Lillicrap, T., Santoro, A., Marris, L., Akerman, C. & Hinton, G. Backpropagation and the brain. Nat. Rev. Neurosci. 21, 335\u2013346 (2020).","journal-title":"Nat. Rev. Neurosci."},{"key":"802_CR37","doi-asserted-by":"publisher","first-page":"464","DOI":"10.1177\/1745691612454304","volume":"7","author":"T Gureckis","year":"2012","unstructured":"Gureckis, T. & Markant, D. Self-directed learning: a cognitive and computational perspective. Perspect. Psychol. Sci. 7, 464\u2013481 (2012).","journal-title":"Perspect. Psychol. Sci."},{"key":"802_CR38","doi-asserted-by":"publisher","unstructured":"Long, B. et al. The BabyView camera: designing a new head-mounted camera to capture children\u2019s early social and visual environments. Behav. Res. Methods https:\/\/doi.org\/10.3758\/s13428-023-02206-1 (2023).","DOI":"10.3758\/s13428-023-02206-1"},{"key":"802_CR39","doi-asserted-by":"crossref","unstructured":"Moore, D., Oakes, L., Romero, V. & McCrink, K. Leveraging developmental psychology to evaluate artificial intelligence. In 2022 IEEE International Conference on Development and Learning (ICDL) 36\u201341 (IEEE, 2022).","DOI":"10.1109\/ICDL53763.2022.9962183"},{"key":"802_CR40","doi-asserted-by":"crossref","unstructured":"Frank, M. C. Bridging the data gap between children and large language models. Trends Cogn. Sci. 27, 990\u2013992 (2023).","DOI":"10.1016\/j.tics.2023.08.007"},{"key":"802_CR41","unstructured":"Object stimuli. Brady Lab https:\/\/bradylab.ucsd.edu\/stimuli\/ObjectCategories.zip"},{"key":"802_CR42","doi-asserted-by":"publisher","first-page":"558","DOI":"10.1037\/a0019165","volume":"139","author":"T Konkle","year":"2010","unstructured":"Konkle, T., Brady, T., Alvarez, G. & Oliva, A. Conceptual distinctiveness supports detailed visual long-term memory for real-world objects. J. Exp. Psychol. Gen. 139, 558 (2010).","journal-title":"J. Exp. Psychol. Gen."},{"key":"802_CR43","unstructured":"Lomonaco, V. & Maltoni, D. CORe50 Dataset. GitHub https:\/\/vlomonaco.github.io\/core50 (2017)."},{"key":"802_CR44","unstructured":"Lomonaco, V. & Maltoni, D. CORe50: a new dataset and benchmark for continuous object recognition. In Proc. 1st Annual Conference on Robot Learning (eds Levine, S. et al.) 17\u201326 (PMLR, 2017)."},{"key":"802_CR45","unstructured":"Russakovsky, O. et al. ImageNet Dataset. https:\/\/www.image-net.org\/download.php (2015)."},{"key":"802_CR46","doi-asserted-by":"publisher","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","volume":"2","author":"R Geirhos","year":"2020","unstructured":"Geirhos, R. et al. Shortcut learning in deep neural networks. Nat. Mach. Intell. 2, 665\u2013673 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"802_CR47","first-page":"23885","volume":"34","author":"R Geirhos","year":"2021","unstructured":"Geirhos, R. et al. Partial success in closing the gap between human and machine vision. Adv. Neur. In. 34, 23885\u201323899 (2021).","journal-title":"Adv. Neur. In."},{"key":"802_CR48","unstructured":"Geirhos, R. et al. ImageNet OOD Dataset. GitHub https:\/\/github.com\/bethgelab\/model-vs-human (2021)."},{"key":"802_CR49","doi-asserted-by":"publisher","first-page":"e2011417118","DOI":"10.1073\/pnas.2011417118","volume":"118","author":"J Mehrer","year":"2021","unstructured":"Mehrer, J., Spoerer, C., Jones, E., Kriegeskorte, N. & Kietzmann, T. An ecologically motivated image dataset for deep learning yields better models of human vision. Proc. Natl Acad. Sci. USA 118, e2011417118 (2021).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"802_CR50","unstructured":"Mehrer, J., Spoerer, C., Jones, E., Kriegeskorte, N. & Kietzmann, T. Ecoset Dataset. Hugging Face https:\/\/huggingface.co\/datasets\/kietzmannlab\/ecoset (2021)."},{"key":"802_CR51","doi-asserted-by":"crossref","unstructured":"Zhou, B., Lapedriza, A., Khosla, A., Oliva, A. & Torralba, A. Places: a 10 million image database for scene recognition. IEEE T. Pattern Anal. 40, 1452\u20131464 (2017).","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"802_CR52","unstructured":"Zhou, B. et al. Places365 Dataset. http:\/\/places2.csail.mit.edu (2017)."},{"key":"802_CR53","unstructured":"Pont-Tuset, J. et al. The 2017 DAVIS challenge on video object segmentation. Preprint at https:\/\/arxiv.org\/abs\/1704.00675 (2017)."},{"key":"802_CR54","unstructured":"Pont-Tuset, J. et al. DAVIS-2017 evaluation code, dataset and results. https:\/\/davischallenge.org\/davis2017\/code.html (2017)."},{"key":"802_CR55","doi-asserted-by":"crossref","unstructured":"Lin, T. et al. Microsoft COCO: common objects in context. In Computer Vision \u2013 ECCV 2014 (eds Fleet, D. et al.) 740\u2013755 (2014).","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"802_CR56","unstructured":"COCO Dataset. https:\/\/cocodataset.org\/#download (2014)."},{"key":"802_CR57","first-page":"19545","volume":"33","author":"A Jabri","year":"2020","unstructured":"Jabri, A., Owens, A. & Efros, A. Space-time correspondence as a contrastive random walk. Adv. Neur. In. 33, 19545\u201319560 (2020).","journal-title":"Adv. Neur. In."},{"key":"802_CR58","unstructured":"Kinetics-700-2020 Dataset. https:\/\/github.com\/cvdfoundation\/kinetics-dataset#kinetics-700-2020 (2020)."},{"key":"802_CR59","unstructured":"Ego4D Dataset. https:\/\/ego4d-data.org\/ (2022)."},{"key":"802_CR60","unstructured":"Kingma, D. & Ba, J. Adam: A method for stochastic optimization. Preprint at https:\/\/arxiv.org\/abs\/1412.6980 (2014)."},{"key":"802_CR61","unstructured":"VQGAN resources. GitHub https:\/\/github.com\/CompVis\/taming-transformers (2021)."},{"key":"802_CR62","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B. & Hochreiter, S. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. Adv. Neural Inf. Process. Syst. 30, 6629\u20136640 (2017)."},{"key":"802_CR63","doi-asserted-by":"publisher","unstructured":"Orhan, A. E. eminorhan\/silicon-menagerie: v1.0.0-alpha. Zenodo https:\/\/doi.org\/10.5281\/zenodo.8322408 (2023).","DOI":"10.5281\/zenodo.8322408"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00802-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00802-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00802-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,11]],"date-time":"2024-06-11T12:55:22Z","timestamp":1718110522000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-024-00802-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,7]]},"references-count":63,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["802"],"URL":"https:\/\/doi.org\/10.1038\/s42256-024-00802-0","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,7]]},"assertion":[{"value":"24 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2024","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"In the version of the article initially published, the name of Cliona O\u2019Doherty was not included in the peer review information for this article, which has now been amended.","order":6,"name":"change_details","label":"Change Details","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}