{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T19:29:38Z","timestamp":1778700578316,"version":"3.51.4"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"7626","license":[{"start":{"date-parts":[[2016,10,12]],"date-time":"2016-10-12T00:00:00Z","timestamp":1476230400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2016,10,12]],"date-time":"2016-10-12T00:00:00Z","timestamp":1476230400000},"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":["Nature"],"published-print":{"date-parts":[[2016,10,27]]},"DOI":"10.1038\/nature20101","type":"journal-article","created":{"date-parts":[[2016,10,12]],"date-time":"2016-10-12T20:17:48Z","timestamp":1476303468000},"page":"471-476","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":908,"title":["Hybrid computing using a neural network with dynamic external memory"],"prefix":"10.1038","volume":"538","author":[{"given":"Alex","family":"Graves","sequence":"first","affiliation":[]},{"given":"Greg","family":"Wayne","sequence":"additional","affiliation":[]},{"given":"Malcolm","family":"Reynolds","sequence":"additional","affiliation":[]},{"given":"Tim","family":"Harley","sequence":"additional","affiliation":[]},{"given":"Ivo","family":"Danihelka","sequence":"additional","affiliation":[]},{"given":"Agnieszka","family":"Grabska-Barwi\u0144ska","sequence":"additional","affiliation":[]},{"given":"Sergio G\u00f3mez","family":"Colmenarejo","sequence":"additional","affiliation":[]},{"given":"Edward","family":"Grefenstette","sequence":"additional","affiliation":[]},{"given":"Tiago","family":"Ramalho","sequence":"additional","affiliation":[]},{"given":"John","family":"Agapiou","sequence":"additional","affiliation":[]},{"given":"Adri\u00e0 Puigdom\u00e8nech","family":"Badia","sequence":"additional","affiliation":[]},{"given":"Karl Moritz","family":"Hermann","sequence":"additional","affiliation":[]},{"given":"Yori","family":"Zwols","sequence":"additional","affiliation":[]},{"given":"Georg","family":"Ostrovski","sequence":"additional","affiliation":[]},{"given":"Adam","family":"Cain","sequence":"additional","affiliation":[]},{"given":"Helen","family":"King","sequence":"additional","affiliation":[]},{"given":"Christopher","family":"Summerfield","sequence":"additional","affiliation":[]},{"given":"Phil","family":"Blunsom","sequence":"additional","affiliation":[]},{"given":"Koray","family":"Kavukcuoglu","sequence":"additional","affiliation":[]},{"given":"Demis","family":"Hassabis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2016,10,12]]},"reference":[{"key":"BFnature20101_CR1","first-page":"1097","volume":"25","author":"A Krizhevsky","year":"2012","unstructured":"Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems Vol. 25 (eds Pereira, F. et al.) 1097\u20131105 (Curran Associates, 2012)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"BFnature20101_CR2","unstructured":"Graves, A. Generating sequences with recurrent neural networks. Preprint at http:\/\/arxiv.org\/abs\/1308.0850 (2013)"},{"key":"BFnature20101_CR3","first-page":"3104","volume":"27","author":"I Sutskever","year":"2014","unstructured":"Sutskever, I., Vinyals, O. & Le, Q. V. Sequence to sequence learning with neural networks. In Advances in Neural Information Processing Systems Vol. 27 (eds Ghahramani, Z. et al.) 3104\u20133112 (Curran Associates, 2014)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"BFnature20101_CR4","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V. et al. Human-level control through deep reinforcement learning. Nature 518, 529\u2013533 (2015)","journal-title":"Nature"},{"key":"BFnature20101_CR5","unstructured":"Gallistel, C. R. & King, A. P. Memory and the Computational Brain: Why Cognitive Science Will Transform Neuroscience (John Wiley & Sons, 2011)"},{"key":"BFnature20101_CR6","doi-asserted-by":"crossref","unstructured":"Marcus, G. F. The Algebraic Mind: Integrating Connectionism and Cognitive Science (MIT Press, 2001)","DOI":"10.7551\/mitpress\/1187.001.0001"},{"key":"BFnature20101_CR7","doi-asserted-by":"publisher","first-page":"16390","DOI":"10.1073\/pnas.1303547110","volume":"110","author":"T Kriete","year":"2013","unstructured":"Kriete, T., Noelle, D. C., Cohen, J. D. & O\u2019Reilly, R. C. Indirection and symbol-like processing in the prefrontal cortex and basal ganglia. Proc. Natl Acad. Sci. USA 110, 16390\u201316395 (2013)","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"BFnature20101_CR8","first-page":"1","volume":"1","author":"GE Hinton","year":"1986","unstructured":"Hinton, G. E. Learning distributed representations of concepts. In Proc. Eighth Annual Conference of the Cognitive Science Society Vol. 1, 1\u201312 (Lawrence Erlbaum Associates, 1986)","journal-title":"Proc. Eighth Annual Conference of the Cognitive Science Society"},{"key":"BFnature20101_CR9","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s10994-013-5335-x","volume":"94","author":"L Bottou","year":"2014","unstructured":"Bottou, L. From machine learning to machine reasoning. Mach. Learn. 94, 133\u2013149 (2014)","journal-title":"Mach. Learn."},{"key":"BFnature20101_CR10","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1016\/j.neuron.2005.02.001","volume":"45","author":"S Fusi","year":"2005","unstructured":"Fusi, S., Drew, P. J. & Abbott, L. F. Cascade models of synaptically stored memories. Neuron 45, 599\u2013611 (2005)","journal-title":"Neuron"},{"key":"BFnature20101_CR11","doi-asserted-by":"publisher","first-page":"18970","DOI":"10.1073\/pnas.0804451105","volume":"105","author":"S Ganguli","year":"2008","unstructured":"Ganguli, S., Huh, D. & Sompolinsky, H. Memory traces in dynamical systems. Proc. Natl Acad. Sci. USA 105, 18970\u201318975 (2008)","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"BFnature20101_CR12","unstructured":"Kanerva, P. Sparse Distributed Memory (MIT press, 1988)"},{"key":"BFnature20101_CR13","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1016\/0893-6080(89)90043-9","volume":"2","author":"S-i Amari","year":"1989","unstructured":"Amari, S.-i . Characteristics of sparsely encoded associative memory. Neural Netw. 2, 451\u2013457 (1989)","journal-title":"Neural Netw"},{"key":"BFnature20101_CR14","unstructured":"Weston, J., Chopra, S. & Bordes, A. Memory networks. Preprint at http:\/\/arxiv.org\/abs\/1410.3916 (2014)"},{"key":"BFnature20101_CR15","first-page":"2692","volume":"28","author":"O Vinyals","year":"2015","unstructured":"Vinyals, O., Fortunato, M. & Jaitly, N. Pointer networks. In Advances in Neural Information Processing Systems Vol. 28 (eds Cortes, C et al.) 2692\u20132700 (Curran Associates, 2015)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"BFnature20101_CR16","unstructured":"Graves, A., Wayne, G. & Danihelka, I. Neural Turing machines. Preprint at http:\/\/arxiv.org\/abs\/1410.5401 (2014)"},{"key":"BFnature20101_CR17","unstructured":"Bahdanau, D., Cho, K. & Bengio, Y. Neural machine translation by jointly learning to align and translate. Preprint at http:\/\/arxiv.org\/abs\/1409.0473 (2014)"},{"key":"BFnature20101_CR18","unstructured":"Gregor, K., Danihelka, I., Graves, A., Rezende, D. J. & Wierstra, D. DRAW: a recurrent neural network for image generation. In Proc. 32nd International Conference on Machine Learning (eds Bach, F. & Blei, D. ) 1462 \u20131471 (JMLR, 2015)"},{"key":"BFnature20101_CR19","doi-asserted-by":"publisher","first-page":"96","DOI":"10.3758\/BF03202365","volume":"16","author":"DL Hintzman","year":"1984","unstructured":"Hintzman, D. L. MINERVA 2: a simulation model of human memory. Behav. Res. Methods Instrum. Comput. 16, 96\u2013101 (1984)","journal-title":"Behav. Res. Methods Instrum. Comput."},{"key":"BFnature20101_CR20","unstructured":"Kumar, A. et al. Ask me anything: dynamic memory networks for natural language processing. Preprint at http:\/\/arxiv.org\/abs\/1506.07285 (2015)"},{"key":"BFnature20101_CR21","first-page":"2431","volume":"Vol. 28","author":"S Sukhbaatar","year":"2015","unstructured":"Sukhbaatar, S. et al. End-to-end memory networks. In Advances in Neural Information Processing Systems Vol. 28 (eds Cortes, C et al.) 2431\u20132439 (Curran Associates, 2015)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"BFnature20101_CR22","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1126\/science.275.5297.209","volume":"275","author":"JC Magee","year":"1997","unstructured":"Magee, J. C. & Johnston, D. A synaptically controlled, associative signal for Hebbian plasticity in hippocampal neurons. Science 275, 209\u2013213 (1997)","journal-title":"Science"},{"key":"BFnature20101_CR23","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.nlm.2015.10.013","volume":"129","author":"ST Johnston","year":"2016","unstructured":"Johnston, S. T., Shtrahman, M., Parylak, S., Gon\u00c7alves, J. T. & Gage, F. H. Paradox of pattern separation and adult neurogenesis: a dual role for new neurons balancing memory resolution and robustness. Neurobiol. Learn. Mem. 129, 60\u201368 (2016)","journal-title":"Neurobiol. Learn. Mem."},{"key":"BFnature20101_CR24","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1002\/hipo.450040605","volume":"4","author":"RC O\u2019Reilly","year":"1994","unstructured":"O\u2019Reilly, R. C. & McClelland, J. L. Hippocampal conjunctive encoding, storage, and recall: avoiding a trade-off. Hippocampus 4, 661\u2013682 (1994)","journal-title":"Hippocampus"},{"key":"BFnature20101_CR25","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1006\/jmps.2001.1388","volume":"46","author":"MW Howard","year":"2002","unstructured":"Howard, M. W. & Kahana, M. J. A distributed representation of temporal context. J. Math. Psychol. 46, 269\u2013299 (2002)","journal-title":"J. Math. Psychol."},{"key":"BFnature20101_CR26","unstructured":"Weston, J., Bordes, A., Chopra, S. & Mikolov, T. Towards AI-complete question answering: a set of prerequisite toy tasks. Preprint at http:\/\/arxiv.org\/abs\/1502.05698 (2015)"},{"key":"BFnature20101_CR27","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S. & Schmidhuber, J. Long short-term memory. Neural Comput. 9, 1735\u20131780 (1997)","journal-title":"Neural Comput"},{"key":"BFnature20101_CR28","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R. & Weston, J. Curriculum learning. In Proc. 26th International Conference on Machine Learning (eds Bottou, L. & Littman, M. ) 41\u201348 (ACM, 2009)","DOI":"10.1145\/1553374.1553380"},{"key":"BFnature20101_CR29","unstructured":"Zaremba, W. & Sutskever, I. Learning to execute. Preprint at http:\/\/arxiv.org\/abs\/1410.4615 (2014)"},{"key":"BFnature20101_CR30","unstructured":"Winograd, T. Procedures as a Representation for Data in a Computer Program for Understanding Natural Language. Report No. MAC-TR-84 (DTIC, MIT Project MAC, 1971)"},{"key":"BFnature20101_CR31","doi-asserted-by":"publisher","first-page":"543","DOI":"10.1126\/science.207.4430.543","volume":"207","author":"R Epstein","year":"1980","unstructured":"Epstein, R., Lanza, R. P. & Skinner, B. F. Symbolic communication between two pigeons (Columba livia domestica). Science 207, 543\u2013545 (1980)","journal-title":"Science"},{"key":"BFnature20101_CR32","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1037\/0033-295X.102.3.419","volume":"102","author":"JL McClelland","year":"1995","unstructured":"McClelland, J. L., McNaughton, B. L. & O\u2019Reilly, R. C. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychol. Rev. 102, 419\u2013457 (1995)","journal-title":"Psychol. Rev."},{"key":"BFnature20101_CR33","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.tics.2016.05.004","volume":"20","author":"D Kumaran","year":"2016","unstructured":"Kumaran, D., Hassabis, D. & McClelland, J. L. What learning systems do intelligent agents need? Complementary learning systems theory updated. Trends Cogn. Sci. 20, 512\u2013534 (2016)","journal-title":"Trends Cogn. Sci."},{"key":"BFnature20101_CR34","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1002\/(SICI)1098-1063(1996)6:6<654::AID-HIPO8>3.0.CO;2-G","volume":"6","author":"JL McClelland","year":"1996","unstructured":"McClelland, J. L. & Goddard, N. H. Considerations arising from a complementary learning systems perspective on hippocampus and neocortex. Hippocampus 6, 654\u2013665 (1996)","journal-title":"Hippocampus"},{"key":"BFnature20101_CR35","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1126\/science.aab3050","volume":"350","author":"BM Lake","year":"2015","unstructured":"Lake, B. M., Salakhutdinov, R. & Tenenbaum, J. B. Human-level concept learning through probabilistic program induction. Science 350, 1332\u20131338 (2015)","journal-title":"Science"},{"key":"BFnature20101_CR36","unstructured":"Rezende, D. J., Mohamed, S., Danihelka, I., Gregor, K. & Wierstra, D. One-shot generalization in deep generative models. In Proc. 33nd International Conference on Machine Learning (eds Balcan, M. F. & Weinberger, K. Q. ) 1521\u20131529 (JMLR, 2016)"},{"key":"BFnature20101_CR37","unstructured":"Santoro, A., Bartunov, S., Botvinick, M., Wierstra, D. & Lillicrap, T. Meta-learning with memory-augmented neural networks. In Proc. 33nd International Conference on Machine Learning (eds Balcan, M. F. & Weinberger, K. Q. ) 1842\u20131850 (JMLR, 2016)"},{"key":"BFnature20101_CR38","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":"BFnature20101_CR39","first-page":"1693","volume":"28","author":"KM Hermann","year":"2015","unstructured":"Hermann, K. M. et al. Teaching machines to read and comprehend. In Advances in Neural Information Processing Systems Vol. 28 (eds Cortes, C. et al.) 1693\u20131701 (Curran Associates, 2015)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"BFnature20101_CR40","unstructured":"O\u2019Keefe, J. & Nadel, L. The Hippocampus as a Cognitive Map (Oxford Univ. Press, 1978)"},{"key":"BFnature20101_CR41","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.-r. & Hinton, G. Speech recognition with deep recurrent neural networks. In IEEE International Conference on Acoustics, Speech and Signal Processing (eds Ward, R. et al.) 6645\u20136649 (Curran Associates, 2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"BFnature20101_CR42","doi-asserted-by":"crossref","unstructured":"Wilson, P. R., Johnstone, M. S., Neely, M. & Boles, D. Dynamic storage allocation: a survey and critical review. In Memory Management (ed. Baler, H. G. ) 1\u2013116 (Springer, 1995)","DOI":"10.1007\/3-540-60368-9_19"},{"key":"BFnature20101_CR43","unstructured":"Ross, S., Gordon, G. J. & Bagnell, J. A. A reduction of imitation learning and structured prediction to no-regret online learning. In Proc. Fourteenth International Conference on Artificial Intelligence and Statistics (eds Gordon, G. et al.) 627\u2013635 (JMLR, 2010)"},{"key":"BFnature20101_CR44","doi-asserted-by":"publisher","first-page":"297","DOI":"10.1007\/s10994-009-5106-x","volume":"75","author":"H Daum\u00e9 III","year":"2009","unstructured":"Daum\u00e9, H. III, Langford, J. & Marcu, D. Search-based structured prediction. Mach. Learn. 75, 297\u2013325 (2009)","journal-title":"Mach. Learn"},{"key":"BFnature20101_CR45","first-page":"229","volume":"8","author":"RJ Williams","year":"1992","unstructured":"Williams, R. J. Simple statistical gradient-following algorithms for connectionist reinforcement learning. Mach. Learn. 8, 229\u2013256 (1992)","journal-title":"Mach. Learn"},{"key":"BFnature20101_CR46","first-page":"1057","volume":"12","author":"RS Sutton","year":"1999","unstructured":"Sutton, R. S., McAllester, D., Singh, S. P. & Mansour, Y. Policy gradient methods for reinforcement learning with function approximation. In Advances in Neural Information Processing Systems Vol. 12 (eds Solla, S. A. et al.) 1057\u20131063 (MIT Press, 1999)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"BFnature20101_CR47","unstructured":"Schulman, J., Moritz, P., Levine, S., Jordan, M. & Abbeel, P. High-dimensional continuous control using generalized advantage estimation. Preprint at http:\/\/arxiv.org\/abs\/1506.02438 (2015)"},{"key":"BFnature20101_CR48","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L. & Hinton, G. Visualizing data using t-SNE. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."},{"key":"BFnature20101_CR49","first-page":"1223","volume":"25","author":"J Dean","year":"2012","unstructured":"Dean, J. et al. Large scale distributed deep networks. In Advances in Neural Information Processing Systems Vol. 25 (eds Pereira, F. et al.) 1223\u20131231 (Curran Associates, 2012)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"BFnature20101_CR50","doi-asserted-by":"publisher","first-page":"1550","DOI":"10.1109\/5.58337","volume":"78","author":"PJ Werbos","year":"1990","unstructured":"Werbos, P. J. Backpropagation through time: what it does and how to do it. Proc. IEEE 78, 1550\u20131560 (1990)","journal-title":"Proc. IEEE"},{"key":"BFnature20101_CR51","unstructured":"Tieleman, T. & Hinton, G. RmsProp: divide the gradient by a running average of its recent magnitude. Lecture 6.5 of Neural Networks for Machine Learning (COURSERA, 2012); available at http:\/\/www.cs.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf"}],"container-title":["Nature"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/nature20101.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/nature20101","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/nature20101.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,20]],"date-time":"2024-03-20T14:14:25Z","timestamp":1710944065000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/nature20101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,10,12]]},"references-count":51,"journal-issue":{"issue":"7626","published-print":{"date-parts":[[2016,10,27]]}},"alternative-id":["BFnature20101"],"URL":"https:\/\/doi.org\/10.1038\/nature20101","relation":{},"ISSN":["0028-0836","1476-4687"],"issn-type":[{"value":"0028-0836","type":"print"},{"value":"1476-4687","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,10,12]]},"assertion":[{"value":"5 January 2016","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2016","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 October 2016","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing financial interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}