{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,18]],"date-time":"2026-11-18T15:33:36Z","timestamp":1795016016403,"version":"4.10.1"},"reference-count":107,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2020,11,10]],"date-time":"2020-11-10T00:00:00Z","timestamp":1604966400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,11,10]],"date-time":"2020-11-10T00:00:00Z","timestamp":1604966400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-020-00257-z","type":"journal-article","created":{"date-parts":[[2020,11,10]],"date-time":"2020-11-10T12:04:19Z","timestamp":1605009859000},"page":"665-673","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2185,"title":["Shortcut learning in deep neural networks"],"prefix":"10.1038","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7698-3187","authenticated-orcid":false,"given":"Robert","family":"Geirhos","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"J\u00f6rn-Henrik","family":"Jacobsen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9812-317X","authenticated-orcid":false,"given":"Claudio","family":"Michaelis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Zemel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wieland","family":"Brendel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Bethge","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2592-634X","authenticated-orcid":false,"given":"Felix A.","family":"Wichmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,10]]},"reference":[{"key":"257_CR1","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In Proc. IEEE Int. Conf. Computer Vision 1026\u20131034 (ACM, 2015).","DOI":"10.1109\/ICCV.2015.123"},{"key":"257_CR2","doi-asserted-by":"publisher","first-page":"484","DOI":"10.1038\/nature16961","volume":"529","author":"D Silver","year":"2016","unstructured":"Silver, D. et al. Mastering the game of Go with deep neural networks and tree search. Nature 529, 484\u2013489 (2016).","journal-title":"Nature"},{"key":"257_CR3","doi-asserted-by":"publisher","first-page":"508","DOI":"10.1126\/science.aam6960","volume":"356","author":"M Morav\u010d\u00edk","year":"2017","unstructured":"Morav\u010d\u00edk, M. et al. Deepstack: expert-level artificial intelligence in heads-up no-limit poker. Science 356, 508\u2013513 (2017).","journal-title":"Science"},{"key":"257_CR4","unstructured":"Rajpurkar, P. et al. CheXNet: radiologist-level pneumonia detection on chest X-rays with deep learning. Preprint at https:\/\/arxiv.org\/abs\/1711.05225 (2017)."},{"key":"257_CR5","unstructured":"Devlin, J., Chang, M. W., Lee, K. & Toutanova, K. BERT: pre-training of deep bidirectional transformers for language understanding. In Proc. Annual Conf. North American Chapter of the Association for Computational Linguistics (ACL, 2019)."},{"key":"257_CR6","unstructured":"Rolnick, D. et al. Tackling climate change with machine learning. Preprint at https:\/\/arxiv.org\/abs\/1906.05433 (2019)."},{"key":"257_CR7","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41586-019-0912-1","volume":"566","author":"M Reichstein","year":"2019","unstructured":"Reichstein, M. et al. Deep learning and process understanding for data-driven earth system science. Nature 566, 195\u2013204 (2019).","journal-title":"Nature"},{"key":"257_CR8","unstructured":"Szegedy, C. et al. Intriguing properties of neural networks. In Proc. Int. Conf. Learning Representations (ICLR, 2014)."},{"key":"257_CR9","doi-asserted-by":"crossref","unstructured":"Beery, S., Van Horn, G. & Perona, P. Recognition in terra incognita. In European Conf. Computer Vision 456\u2013473 (Springer, 2018).","DOI":"10.1007\/978-3-030-01270-0_28"},{"key":"257_CR10","unstructured":"Rosenfeld, A., Zemel, R. & Tsotsos, J. K. The elephant in the room. Preprint at https:\/\/arxiv.org\/abs\/1808.03305 (2018)."},{"key":"257_CR11","unstructured":"Heuer, H., Monz, C. & Smeulders, A. W. Generating captions without looking beyond objects. Preprint at https:\/\/arxiv.org\/abs\/1610.03708 (2016)."},{"key":"257_CR12","unstructured":"Buolamwini, J. & Gebru, T. Gender shades: Intersectional accuracy disparities in commercial gender classification. In Proc. ACM Fairness Accountability and Transparency 77\u201391 (PMLR, 2018)."},{"key":"257_CR13","unstructured":"Dastin, J. Amazon scraps secret AI recruiting tool that showed bias against women. Reuters https:\/\/reut.rs\/2Od9fPr (2018)."},{"key":"257_CR14","unstructured":"Shane, J. Do neural nets dream of electric sheep? AI Wierdness https:\/\/aiweirdness.com\/post\/171451900302\/do-neural-nets-dream-of-electric-sheep (2018)."},{"key":"257_CR15","doi-asserted-by":"crossref","unstructured":"Niven, T. & Kao, H.-Y. Probing neural network comprehension of natural language arguments. In Proc. 57th Annual Meeting of the Association of Computational Linguistics 4658\u20134664 (2019).","DOI":"10.18653\/v1\/P19-1459"},{"key":"257_CR16","doi-asserted-by":"crossref","unstructured":"Jia, R. & Liang, P. Adversarial examples for evaluating reading comprehension systems. Preprint at https:\/\/arxiv.org\/1707.07328 (2017).","DOI":"10.18653\/v1\/D17-1215"},{"key":"257_CR17","doi-asserted-by":"publisher","first-page":"e1002683","DOI":"10.1371\/journal.pmed.1002683","volume":"15","author":"JR Zech","year":"2018","unstructured":"Zech, J. R. et al. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med. 15, e1002683 (2018).","journal-title":"PLoS Med."},{"key":"257_CR18","first-page":"2137","volume":"10","author":"S Bickel","year":"2009","unstructured":"Bickel, S., Bru\u00a8ckner, M. & Scheffer, T. Discriminative learning under covariate shift. J. Mach. Learn. Res. 10, 2137\u20132155 (2009).","journal-title":"J. Mach. Learn. Res."},{"key":"257_CR19","unstructured":"Sch\u00f6lkopf, B. et al. On causal and anticausal learning. In Proc. Int. Conf. Machine Learning 1255\u20131262 (ICML, 2012)."},{"key":"257_CR20","doi-asserted-by":"crossref","unstructured":"Torralba, A. & Efros, A. A. Unbiased look at dataset bias. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2011).","DOI":"10.1109\/CVPR.2011.5995347"},{"key":"257_CR21","unstructured":"Branwen, G. The neural net tank urban legend. Gwern.net https:\/\/www.gwern.net\/Tanks (2011)."},{"key":"257_CR22","doi-asserted-by":"crossref","unstructured":"Pfungst, O. Clever Hans (The Horse of Mr. Von Osten): A Contribution to Experimental Animal and Human Psychology (Holt, Rinehart and Winston, 1911).","DOI":"10.5962\/bhl.title.56164"},{"key":"257_CR23","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1023\/A:1003196224280","volume":"35","author":"K Scouller","year":"1998","unstructured":"Scouller, K. The influence of assessment method on students\u2019 learning approaches: multiple choice question examination versus assignment essay. Higher Educ. 35, 453\u2013472 (1998).","journal-title":"Higher Educ."},{"key":"257_CR24","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1167\/10.4.6","volume":"10","author":"FA Wichmann","year":"2010","unstructured":"Wichmann, F. A., Drewes, J., Rosas, P. & Gegenfurtner, K. R. Animal detection in natural scenes: critical features revisited. J. Vis. 10, 6 (2010).","journal-title":"J. Vis."},{"key":"257_CR25","doi-asserted-by":"crossref","unstructured":"Ribeiro, M. T., Singh, S. & Guestrin, C. \u201cWhy should I trust you?\u201d: Explaining the predictions of any classifier. In Proc. 22nd ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining 1135\u20131144 (ACM, 2016).","DOI":"10.1145\/2939672.2939778"},{"key":"257_CR26","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Xie, L. & Yuille, A. L. Object recognition with and without objects. In Proc. 26th Int. Joint Conf. Artificial Intelligence 3609\u20133615 (IJCAI, 2017).","DOI":"10.24963\/ijcai.2017\/505"},{"key":"257_CR27","doi-asserted-by":"crossref","first-page":"151","DOI":"10.4310\/AMSA.2018.v3.n1.a5","volume":"3","author":"J Wang","year":"2018","unstructured":"Wang, J. et al. Visual concepts and compositional voting. Ann. Math. Sci. Appl. 3, 151\u2013188 (2018).","journal-title":"Ann. Math. Sci. Appl."},{"key":"257_CR28","doi-asserted-by":"crossref","unstructured":"Dawson, M., Zisserman, A. & Nell\u00e5ker, C. From same photo: cheating on visual kinship challenges. In Asian Conf. Computer Vision 654\u2013668 (Springer, 2018).","DOI":"10.1007\/978-3-030-20893-6_41"},{"key":"257_CR29","unstructured":"Biederman, I. On the Semantics of a Glance at a Scene (Erlbaum, 1981)."},{"key":"257_CR30","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/0010-0285(82)90007-X","volume":"14","author":"I Biederman","year":"1982","unstructured":"Biederman, I., Mezzanotte, R. J. & Rabinowitz, J. C. Scene perception: detecting and judging objects undergoing relational violations. Cogn. Psychol. 14, 143\u2013177 (1982).","journal-title":"Cogn. Psychol."},{"key":"257_CR31","doi-asserted-by":"publisher","first-page":"520","DOI":"10.1016\/j.tics.2007.09.009","volume":"11","author":"A Oliva","year":"2007","unstructured":"Oliva, A. & Torralba, A. The role of context in object recognition. Trends Cogn. Sci. 11, 520\u2013527 (2007).","journal-title":"Trends Cogn. Sci."},{"key":"257_CR32","doi-asserted-by":"publisher","first-page":"890","DOI":"10.3758\/s13423-011-0107-8","volume":"18","author":"MS Castelhano","year":"2011","unstructured":"Castelhano, M. S. & Heaven, C. Scene context influences without scene gist: eye movements guided by spatial associations in visual search. Psychon. Bull Rev. 18, 890\u2013896 (2011).","journal-title":"Psychon. Bull Rev."},{"key":"257_CR33","unstructured":"Jo, J. & Bengio, Y. Measuring the tendency of CNNs to learn surface statistical regularities. Preprint at https:\/\/arxiv.org\/abs\/1711.11561 (2017)."},{"key":"257_CR34","unstructured":"Ilyas, A. et al. Adversarial examples are not bugs, they are features. In Proc. Advances NeurIPS 125\u2013136 (NeurIPS, 2019)."},{"key":"257_CR35","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1109\/4235.585893","volume":"1","author":"DH Wolpert","year":"1997","unstructured":"Wolpert, D. H. & Macready, W. G. No free lunch theorems for optimization. IEEE T. Evolut. Comput. 1, 67\u201382 (1997).","journal-title":"IEEE T. Evolut. Comput."},{"key":"257_CR36","unstructured":"Brendel, W. & Bethge, M. Approximating CNNs with bag-of-local-features models works surprisingly well on ImageNet. In Proc. Int. Conf. Learning Representations (ICLR, 2019)."},{"key":"257_CR37","doi-asserted-by":"publisher","first-page":"e1006613","DOI":"10.1371\/journal.pcbi.1006613","volume":"14","author":"N Baker","year":"2018","unstructured":"Baker, N., Lu, H., Erlikhman, G. & Kellman, P. J. Deep convolutional networks do not classify based on global object shape. PLoS Comp. Biol. 14, e1006613 (2018).","journal-title":"PLoS Comp. Biol."},{"key":"257_CR38","unstructured":"Geirhos, R. et al. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. In Proc. Int. Conf. Learning Representations (ICLR, 2019)."},{"key":"257_CR39","unstructured":"Heinze-Deml, C. & Meinshausen, N. Conditional variance penalties and domain shift robustness. Preprint at https:\/\/arxiv.org\/abs\/1710.11469 (2017)."},{"key":"257_CR40","unstructured":"Malhotra, G. & Bowers, J. What a difference a pixel makes: an empirical examination of features used by CNNs for categorisation. In Proc. Int. Conf. Learning Representations (ICLR, 2019)."},{"key":"257_CR41","unstructured":"Jacobsen, J.-H., Behrmann, J., Zemel, R. & Bethge, M. Excessive invariance causes adversarial vulnerability. In Proc. Int. Conf. Learning Representations (ICLR, 2019)."},{"key":"257_CR42","unstructured":"Kamin, L. J. Predictability, surprise, attention, and conditioning. In Symp. Punishment and Averse Behavior (eds Campbell, B. A. & Church, R. M.) 279\u2013296 (Appleton-Century-Crofts, 1969)."},{"key":"257_CR43","unstructured":"Dickinson, A. Contemporary Animal Learning Theory Vol. 1 (CUP Archive, 1980)."},{"key":"257_CR44","unstructured":"Bouton, M. E. Learning and Behavior: A Contemporary Synthesis (Sinauer Associates, 2007)."},{"key":"257_CR45","doi-asserted-by":"crossref","unstructured":"Nguyen, A., Yosinski, J. & Clune, J. Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In Proc. IEEE Conf. Computer Vision and Pattern Recognition 427\u2013436 (IEEE, 2015).","DOI":"10.1109\/CVPR.2015.7298640"},{"key":"257_CR46","unstructured":"Hendrycks, D., Zhao, K., Basart, S., Steinhardt, J. & Song, D. Natural adversarial examples. Preprint at https:\/\/arxiv.org\/abs\/1907.07174 (2019)."},{"key":"257_CR47","doi-asserted-by":"publisher","first-page":"135","DOI":"10.1016\/j.neucom.2018.05.083","volume":"312","author":"M Wang","year":"2018","unstructured":"Wang, M. & Deng, W. Deep visual domain adaptation: a survey. Neurocomputing 312, 135\u2013153 (2018).","journal-title":"Neurocomputing"},{"key":"257_CR48","doi-asserted-by":"crossref","unstructured":"Alcorn, M. A. et al. Strike (with) a pose: neural networks are easily fooled by strange poses of familiar objects. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2019).","DOI":"10.1109\/CVPR.2019.00498"},{"key":"257_CR49","first-page":"1","volume":"20","author":"A Azulay","year":"2019","unstructured":"Azulay, A. & Weiss, Y. Why do deep convolutional networks generalize so poorly to small image transformations? J. Mach. Learn. Res. 20, 1\u201325 (2019).","journal-title":"J. Mach. Learn. Res."},{"key":"257_CR50","first-page":"7","volume":"16","author":"S Dodge","year":"2019","unstructured":"Dodge, S. & Karam, L. Human and DNN classification performance on images with quality distortions: a comparative study. ACM T. Appl. Perc. 16, 7 (2019).","journal-title":"ACM T. Appl. Perc."},{"key":"257_CR51","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":"257_CR52","doi-asserted-by":"crossref","unstructured":"Gururangan, S. et al. Annotation artifacts in natural language inference data. In Proc. Annual Conf. North American Chapter of the Association for Computational Linguistics (ACL, 2018).","DOI":"10.18653\/v1\/N18-2017"},{"key":"257_CR53","doi-asserted-by":"crossref","unstructured":"Zellers, R., Holtzman, A., Bisk, Y., Farhadi, A. & Choi, Y. HellaSwag: can a machine really finish your sentence? In Proc. 57th Annual Meeting Assocciation of Computational Linguistics 4791\u20134800 (ACL, 2019).","DOI":"10.18653\/v1\/P19-1472"},{"key":"257_CR54","doi-asserted-by":"crossref","unstructured":"Borowski, J. et al. The notorious difficulty of comparing human and machine perception. In Proc. NeurIPS Shared Representations in Human and Machine Intelligence Workshop (NeurIPS, 2019).","DOI":"10.32470\/CCN.2019.1295-0"},{"key":"257_CR55","unstructured":"Geirhos, R., Meding, K. & Wichmann, F. A. Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency. Preprint at https:\/\/arxiv.org\/abs\/2006.16736 (2020)."},{"key":"257_CR56","unstructured":"Marr, D. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information (W. H. Freeman and Company, 1982)."},{"key":"257_CR57","unstructured":"Buckner, C. The Comparative Psychology of Artificial Intelligences (PhilSci Archive, 2019); http:\/\/philsci-archive.pitt.edu\/16034\/"},{"key":"257_CR58","doi-asserted-by":"crossref","unstructured":"Morgan, C. L. Introduction to Comparative Psychology (Scribner, 1903).","DOI":"10.1037\/13701-000"},{"key":"257_CR59","unstructured":"Ghahramani, Z. Panel of workshop on advances in approximate Bayesian inference (AABI) 2017. YouTube https:\/\/www.youtube.com\/watch?v=x1UByHT60mQ (2017)."},{"key":"257_CR60","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1111\/j.2044-8279.1976.tb02304.x","volume":"46","author":"F Marton","year":"1976","unstructured":"Marton, F. & S\u00e4alj\u00f6, R. On qualitative differences in learning\u2014II Outcome as a function of the learner\u2019s conception of the task. Br. J. Educ. Psychol. 46, 115\u2013127 (1976).","journal-title":"Br. J. Educ. Psychol."},{"key":"257_CR61","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/BF01680526","volume":"8","author":"J Biggs","year":"1979","unstructured":"Biggs, J. Individual differences in study processes and the quality of learning outcomes. Higher Educ. 8, 381\u2013394 (1979).","journal-title":"Higher Educ."},{"key":"257_CR62","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1002\/(SICI)1098-2736(200002)37:2<109::AID-TEA3>3.0.CO;2-7","volume":"37","author":"C Chin","year":"2000","unstructured":"Chin, C. & Brown, D. E. Learning in science: a comparison of deep and surface approaches. J. Res. Sci. Teach. 37, 109\u2013138 (2000).","journal-title":"J. Res. Sci. Teach."},{"key":"257_CR63","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1006\/cogp.1998.0694","volume":"37","author":"GF Marcus","year":"1998","unstructured":"Marcus, G. F. Rethinking eliminative connectionism. Cogn. Psychol. 37, 243\u2013282 (1998).","journal-title":"Cogn. Psychol."},{"key":"257_CR64","unstructured":"Kilbertus, N., Parascandolo, G. & Sch\u00f6lkopf, B. Generalization in anti-causal learning. Preprint at https:\/\/arxiv.org\/abs\/1812.00524 (2018)."},{"key":"257_CR65","unstructured":"Marcus, G. Deep learning: a critical appraisal. Preprint at https:\/\/arxiv.org\/abs\/1801.00631 (2018)."},{"key":"257_CR66","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4","volume":"10","author":"S Lapuschkin","year":"2019","unstructured":"Lapuschkin, S. et al. Unmasking Clever Hans predictors and assessing what machines really learn. Nat. Commun. 10, 1096 (2019).","journal-title":"Nat. Commun."},{"key":"257_CR67","doi-asserted-by":"publisher","first-page":"e253","DOI":"10.1017\/S0140525X16001837","volume":"40","author":"BM Lake","year":"2017","unstructured":"Lake, B. M., Ullman, T. D., Tenenbaum, J. B. & Gershman, S. J. Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017).","journal-title":"Behav. Brain Sci."},{"key":"257_CR68","unstructured":"Chollet, F. The measure of intelligence. Preprint at https:\/\/arxiv.org\/abs\/1911.01547 (2019)."},{"key":"257_CR69","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1038\/s42256-019-0050-3","volume":"1","author":"M Crosby","year":"2019","unstructured":"Crosby, M., Beyret, B. & Halina, M. The Animal-AI Olympics. Nat. Mach. Int. 1, 257\u2013257 (2019).","journal-title":"Nat. Mach. Int."},{"key":"257_CR70","doi-asserted-by":"crossref","unstructured":"Juliani, A. et al. Obstacle tower: a generalization challenge in vision, control, and planning. In Proc. 28th Int. Joint Conf. Artificial Intelligence (IJCAI, 2019).","DOI":"10.24963\/ijcai.2019\/373"},{"key":"257_CR71","unstructured":"Hendrycks, D. & Dietterich, T. Benchmarking neural network robustness to common corruptions and perturbations. In Proc. Int. Conf. Learning Representations (ICLR, 2019)."},{"key":"257_CR72","unstructured":"Levesque, H., Davis, E. & Morgenstern, L. The Winograd Schema Challenge. In 13th Int. Conf. Principles of Knowledge Representation and Reasoning (KR, 2012)."},{"key":"257_CR73","doi-asserted-by":"crossref","unstructured":"Trichelair, P., Emami, A., Trischler, A., Suleman, K. & Cheung, J. C. K. How reasonable are common-sense reasoning tasks: a case-study on the Winograd Schema Challenge and SWAG. In Proc. Conf. Empirical Methods in Natural Language Processing and Int. Joint Conf. Natural Language Processing 3373\u20133378 (ACL, 2019).","DOI":"10.18653\/v1\/D19-1335"},{"key":"257_CR74","unstructured":"Zipf, G. K. Human Behavior and the Principle of Least Effort (Addison-Wesley, 1949)."},{"key":"257_CR75","doi-asserted-by":"publisher","first-page":"258","DOI":"10.1017\/CBO9780511627736.014","volume":"1","author":"JJ Ohala","year":"1990","unstructured":"Ohala, J. J. The phonetics and phonology of aspects of assimilation. Papers Lab. Phono. 1, 258\u2013275 (1990).","journal-title":"Papers Lab. Phono."},{"key":"257_CR76","first-page":"37","volume":"3","author":"A Vicentini","year":"2003","unstructured":"Vicentini, A. The economy principle in language. Notes and Observations from early modern English grammars. Mots Palabras Words 3, 37\u201357 (2003).","journal-title":"Mots Palabras Words"},{"key":"257_CR77","doi-asserted-by":"publisher","first-page":"967","DOI":"10.1016\/j.neuron.2019.08.034","volume":"103","author":"FH Sinz","year":"2019","unstructured":"Sinz, F. H., Pitkow, X., Reimer, J., Bethge, M. & Tolias, A. S. Engineering a less artificial intelligence. Neuron 103, 967\u2013979 (2019).","journal-title":"Neuron"},{"key":"257_CR78","unstructured":"Arpit, D. et al. A closer look at memorization in deep networks. In Proc. Int. Conf. Machine Learning (ICML, 2017)."},{"key":"257_CR79","unstructured":"Valle-Perez, G., Camargo, C. Q. & Louis, A. A. Deep learning generalizes because the parameter-function map is biased towards simple functions. In Proc. Int. Conf. Learning Representations (ICLR, 2018)."},{"key":"257_CR80","unstructured":"Shah, H., Tamuly, K., Raghunathan, A., Jain, P. & Netrapalli, P. The pitfalls of simplicity bias in neural networks. Preprint at https:\/\/arxiv.org\/abs\/2006.07710 (2020)."},{"key":"257_CR81","unstructured":"Kalimeris, D. et al. SGD on neural networks learns functions of increasing complexity. In Proc. Advances NeurIPS 3496\u20133506 (NeurIPS, 2019)."},{"key":"257_CR82","unstructured":"Hermann, K. L. & Lampinen, A. K. What shapes feature representations? exploring datasets, architectures, and training. Preprint at https:\/\/arxiv.org\/abs\/2006.12433 (2020)."},{"key":"257_CR83","unstructured":"Richardson, J. Vectors: Aphorisms & Ten-Second Essays (Ausable, 2001)."},{"key":"257_CR84","doi-asserted-by":"crossref","unstructured":"Engstrom, L. et al. A discussion of \u2018adversarial examples are not bugs, they are features\u2019. Distill https:\/\/distill.pub\/2019\/advex-bugs-discussion\/ (2019).","DOI":"10.23915\/distill.00019"},{"key":"257_CR85","unstructured":"Barbu, A. et al. ObjectNet: a large-scale bias-controlled dataset for pushing the limits of object recognition models. In Proc. Advances NeurIPS 9448\u20139458 (NeurIPS, 2019)."},{"key":"257_CR86","doi-asserted-by":"crossref","unstructured":"Li, D., Yang, Y., Song, Y.-Z. & Hospedales, T. M. Deeper, broader and artier domain generalization. In Proc. IEEE Int. Conf. Computer Vision (IEEE, 2017).","DOI":"10.1109\/ICCV.2017.591"},{"key":"257_CR87","doi-asserted-by":"crossref","unstructured":"Qiu, W. & Yuille, A. UnrealCV: connecting computer vision to unreal engine. In European Conf. Computer Vision 909\u2013916 (Springer, 2016).","DOI":"10.1007\/978-3-319-49409-8_75"},{"key":"257_CR88","unstructured":"Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A. & Koltun, V. CARLA: an open urban driving simulator. In Conf. Robot Learning 1\u201316 (CoRL, 2017)."},{"key":"257_CR89","unstructured":"Creager, E. et al. Flexibly fair representation learning by disentanglement. In Proc. Int. Conf. Machine Learning (ICML, 2019)."},{"key":"257_CR90","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/1276377.1276382","volume":"26","author":"J Hays","year":"2007","unstructured":"Hays, J. & Efros, A. A. Scene completion using millions of photographs. ACM Trans. Graph. 26, 4 (2007).","journal-title":"ACM Trans. Graph."},{"key":"257_CR91","doi-asserted-by":"crossref","unstructured":"Hays, J. & Efros, A. A. IM2GPS: estimating geographic information from a single image. In Proc. IEEE Conf. Computer Vision and Pattern Recognition (IEEE, 2008).","DOI":"10.1109\/CVPR.2008.4587784"},{"key":"257_CR92","doi-asserted-by":"crossref","unstructured":"Poliak, A., Naradowsky, J., Haldar, A., Rudinger, R. & Van Durme, B. Hypothesis only baselines in natural language inference. In Proc. 7th Joint Conf. Lexical and Computational Semantics 180\u2013191 (ACL, 2018).","DOI":"10.18653\/v1\/S18-2023"},{"key":"257_CR93","doi-asserted-by":"crossref","unstructured":"Jasani, B., Girdhar, R. & Ramanan, D. Are we asking the right questions in MovieQA? In Proc. IEEE\/CVF Int. Conf. Computer Vision Workshop (IEEE, 2019).","DOI":"10.1109\/ICCVW.2019.00235"},{"key":"257_CR94","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"K Hornik","year":"1989","unstructured":"Hornik, K., Stinchcombe, M. & White, H. Multilayer feedforward networks are universal approximators. Neural Netw. 2, 359\u2013366 (1989).","journal-title":"Neural Netw."},{"key":"257_CR95","unstructured":"d\u2019Ascoli, S., Sagun, L., Bruna, J. & Biroli, G. Finding the needle in the haystack with convolutions: on the benefits of architectural bias. In Proc. Advances NeurIPS (NeurIPS, 2019)."},{"key":"257_CR96","unstructured":"Ulyanov, D., Vedaldi, A. & Lempitsky, V. Deep image prior. In Proc. IEEE\/CVF Conf. Computer Vision and Pattern Recognition 9446\u20139454 (IEEE, 2018)."},{"key":"257_CR97","unstructured":"Vaswani, A. et al. Attention is all you need. In Proc. Advances NeurIPS 5998\u20136008 (NeurIPS, 2017)."},{"key":"257_CR98","doi-asserted-by":"crossref","unstructured":"Hein, M., Andriushchenko, M. & Bitterwolf, J. Why ReLU networks yield high-confidence predictions far away from the training data and how to mitigate the problem. In Proc. IEEE Conf. Computer Vision and Pattern Recognition 41\u201350 (IEEE, 2019).","DOI":"10.1109\/CVPR.2019.00013"},{"key":"257_CR99","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1162\/artl_a_00319","volume":"26","author":"J Lehman","year":"2020","unstructured":"Lehman, J. et al. The surprising creativity of digital evolution: a collection of anecdotes from the evolutionary computation and artificial life research communities. Art. Life 26, 274\u2013306 (2020).","journal-title":"Art. Life"},{"key":"257_CR100","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D. & Vladu, A. Towards deep learning models resistant to adversarial attacks. In Proc. Int. Conf. Learning Representations (ICLR, 2018)."},{"key":"257_CR101","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I. & Lopez-Paz, D. Invariant risk minimization. Preprint at https:\/\/arxiv.org\/abs\/1907.02893 (2019)."},{"key":"257_CR102","unstructured":"Wu, L., Zhu, Z. & E, W. Towards understanding generalization of deep learning: perspective of loss landscapes. Preprint at https:\/\/arxiv.org\/abs\/1706.10239 (2017)."},{"key":"257_CR103","unstructured":"De Palma, G., Kiani, B. T. & Lloyd, S. Deep neural networks are biased towards simple functions. Preprint at https:\/\/arxiv.org\/abs\/1812.10156 (2018)."},{"key":"257_CR104","unstructured":"Valle-Perez, G., Camargo, C. Q. & Louis, A. A. Deep learning generalizes because the parameter-function map is biased towards simple functions. In Proc. Int. Conf. Learning Representations (ICLR, 2019)."},{"key":"257_CR105","unstructured":"Sun, K. & Nielsen, F. Lightlike neuromanifolds, Occam\u2019s razor and deep learning. Preprint at https:\/\/arxiv.org\/abs\/1905.11027 (2019)."},{"key":"257_CR106","unstructured":"Li, Y., Wei, C. & Ma, T. Towards explaining the regularization effect of initial large learning rate in training neural networks. In Proc. Advances NeurIPS 11674\u201311685 (NeurIPS, 2019)."},{"key":"257_CR107","doi-asserted-by":"publisher","unstructured":"Bartlett, P. L., Long, P. M., Lugosi, G. & Tsigler, A. Benign overfitting in linear regression. Proc. Natl Acad Sci. USA https:\/\/doi.org\/10.1073\/pnas.1907378117 (2019).","DOI":"10.1073\/pnas.1907378117"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-00257-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-00257-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-00257-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,6]],"date-time":"2022-12-06T23:07:10Z","timestamp":1670368030000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-020-00257-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,11,10]]},"references-count":107,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2020,11]]}},"alternative-id":["257"],"URL":"https:\/\/doi.org\/10.1038\/s42256-020-00257-z","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,11,10]]},"assertion":[{"value":"25 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 October 2020","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 November 2020","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}