{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T11:36:37Z","timestamp":1776339397007,"version":"3.51.2"},"reference-count":87,"publisher":"Association for Computing Machinery (ACM)","issue":"7","license":[{"start":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T00:00:00Z","timestamp":1624233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["Commun. ACM"],"published-print":{"date-parts":[[2021,7]]},"abstract":"<jats:p>How can neural networks learn the rich internal representations required for difficult tasks such as recognizing objects or understanding language?<\/jats:p>","DOI":"10.1145\/3448250","type":"journal-article","created":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T15:36:51Z","timestamp":1624289811000},"page":"58-65","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":557,"title":["Deep learning for AI"],"prefix":"10.1145","volume":"64","author":[{"given":"Yoshua","family":"Bengio","sequence":"first","affiliation":[{"name":"Universit\u00e9 de Montr\u00e9al"}]},{"given":"Yann","family":"Lecun","sequence":"additional","affiliation":[{"name":"New York University"}]},{"given":"Geoffrey","family":"Hinton","sequence":"additional","affiliation":[{"name":"University of Toronto, Canada"}]}],"member":"320","published-online":{"date-parts":[[2021,6,21]]},"reference":[{"key":"e_1_2_1_1_1","first-page":"283","article-title":"Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symp","volume":"265","author":"Abadi M.","year":"2016","unstructured":"Abadi, M. et al. Tensorflow: A system for large-scale machine learning. In Proceedings of the 12th USENIX Symp. Operating Systems Design and Implementation, 2016, 265--283.","journal-title":"Operating Systems Design and Implementation"},{"key":"e_1_2_1_2_1","volume-title":"Towards a human-like open-domain chatbot 2020","author":"Adiwardana D.","year":"2001","unstructured":"Adiwardana, D., Luong, M., So, D., Hall, J., Fiedel, N., Thoppilan, R., Yang, Z., Kulshreshtha, A., Nemade, G., Lu, Y., et al. Towards a human-like open-domain chatbot 2020; arXiv preprint arXiv:2001.09977."},{"key":"e_1_2_1_3_1","volume-title":"Invariant risk minimization","author":"Arjovsky M.","year":"2019","unstructured":"Arjovsky, M., Bottou, L., Gulrajani, I., and Lopez-Paz, D. Invariant risk minimization, 2019; arXiv preprint arXiv:1907.02893."},{"key":"e_1_2_1_4_1","first-page":"4339","article-title":"Using fast weights to attend to the recent past","volume":"4331","author":"Ba J.","year":"2016","unstructured":"Ba, J., Hinton, G., Mnih, V., Leibo, J., and Ionescu, C. Using fast weights to attend to the recent past. Advances in Neural Information Processing Systems, 2016, 4331--4339.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_5_1","volume-title":"A Cognitive Theory of Consciousness","author":"Baars B.","year":"1993","unstructured":"Baars, B. A Cognitive Theory of Consciousness. Cambridge University Press, Cambridge, MA, 1993."},{"key":"e_1_2_1_6_1","first-page":"15545","article-title":"Learning representations by maximizing mutual information across views","volume":"15535","author":"Bachman P.","year":"2019","unstructured":"Bachman, P., Hjelm, R., and Buchwalter, W. Learning representations by maximizing mutual information across views. Advances in Neural Information Processing Systems, 2019, 15535--15545.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_7_1","volume-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau D.","year":"2014","unstructured":"Bahdanau, D., Cho, K., and Bengio, Y. Neural machine translation by jointly learning to align and translate, 2014; arXiv:1409.0473."},{"key":"e_1_2_1_8_1","volume-title":"Systematic generalization: What is required and can it be learned? 2018","author":"Bahdanau D.","year":"1811","unstructured":"Bahdanau, D., Murty, S., Noukhovitch, M., Nguyen, T., Vries, H., and Courville, A. Systematic generalization: What is required and can it be learned? 2018; arXiv:1811.12889."},{"key":"e_1_2_1_9_1","volume-title":"Closure: Assessing systematic generalization of clever models","author":"Bahdanau D.","year":"2019","unstructured":"Bahdanau, D., de Vries, H., O'Donnell, T., Murty, S., Beaudoin, P., Bengio, Y., and Courville, A. Closure: Assessing systematic generalization of clever models, 2019; arXiv:1912.05783."},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/355161a0"},{"key":"e_1_2_1_11_1","volume-title":"The consciousness prior","author":"Bengio Y.","year":"2017","unstructured":"Bengio, Y. The consciousness prior, 2017; arXiv:1709.08568."},{"key":"e_1_2_1_12_1","volume-title":"Proceedings of the IEEE 1991 Seattle Intern. Joint Conf. Neural Networks 2.","author":"Bengio Y.","unstructured":"Bengio, Y., Bengio, S., and Cloutier, J. Learning a synaptic learning rule. In Proceedings of the IEEE 1991 Seattle Intern. Joint Conf. Neural Networks 2."},{"key":"e_1_2_1_13_1","volume-title":"Proceedings of ICLR'2020; arXiv:1901","author":"Bengio Y.","unstructured":"Bengio, Y., Deleu, T., Rahaman, N., Ke, R., Lachapelle, S., Bilaniuk, O., Goyal, A., and Pal, C. A meta-transfer objective for learning to disentangle causal mechanisms. In Proceedings of ICLR'2020; arXiv:1901.10912."},{"key":"e_1_2_1_14_1","volume-title":"NIPS'2000","author":"Bengio Y.","year":"2001","unstructured":"Bengio, Y., Ducharme, R., and Vincent, P. A neural probabilistic language model. NIPS'2000, 2001, 932--938."},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.25080\/Majora-92bf1922-003"},{"key":"e_1_2_1_17_1","first-page":"744","article-title":"Signature verification using a \"Siamese\" time delay neural network","volume":"737","author":"Bromley J.","year":"1994","unstructured":"Bromley, J., Guyon, I., LeCun, Y., S\u00e4kinger, E., and Shah, R. Signature verification using a \"Siamese\" time delay neural network. Advances in Neural Information Processing Systems, 1994, 737--744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_18_1","volume-title":"et al. Language models are few-shot learners","author":"Brown T.","year":"2020","unstructured":"Brown, T. et al. Language models are few-shot learners, 2020; arXiv:2005.14165."},{"key":"e_1_2_1_19_1","volume-title":"Procedings of ECCV'2020; arXiv:2005","author":"Carion N.","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., and Zagoruyko, S. End-to-end object detection with transformers. In Procedings of ECCV'2020; arXiv:2005.12872."},{"key":"e_1_2_1_20_1","volume-title":"Unsupervised learning of visual features by contrasting cluster assignments","author":"Caron M.","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., and Joulin, A. Unsupervised learning of visual features by contrasting cluster assignments, 2020;. arXiv:2006.09882."},{"key":"e_1_2_1_21_1","volume-title":"A simple framework for contrastive learning of visual representations","author":"Chen T.","year":"2020","unstructured":"Chen, T., Kornblith, S., Norouzi, M., and Hinton, G. A simple framework for contrastive learning of visual representations, 2020; arXiv:2002.05709."},{"key":"e_1_2_1_22_1","volume-title":"Improved baselines with momentum contrastive learning","author":"Chen X.","year":"2020","unstructured":"Chen, X., Fan, H., Girshick, R., and He, K. Improved baselines with momentum contrastive learning, 2020; arXiv:2003.04297."},{"key":"e_1_2_1_23_1","volume-title":"Proceedings in ICLR'2019; arXiv:1810","author":"Chevalier-Boisvert M.","unstructured":"Chevalier-Boisvert, M., Bahdanau, D., Lahlou, S., Willems, L., Saharia, C., Nguyen, T., and Bengio, Y. Babyai: First steps towards grounded language learning with a human in the loop. In Proceedings in ICLR'2019; arXiv:1810.08272."},{"key":"e_1_2_1_24_1","volume-title":"Proceedings of the 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition 1, 539--546","author":"Chopra S.","unstructured":"Chopra, S., Hadsell, R., and LeCun, Y. Learning a similarity metric discriminatively, with application to face verification. In Proceedings of the 2005 IEEE Computer Society Conf. Computer Vision and Pattern Recognition 1, 539--546."},{"key":"e_1_2_1_25_1","volume-title":"Proceedings of NIPS Worskshop BigLearn","author":"Collobert R.","year":"2011","unstructured":"Collobert, R., Kavukcuoglu, K., and Farabet, C. Torch7: A matlab-like environment for machine learning. In Proceedings of NIPS Worskshop BigLearn, 2011."},{"key":"e_1_2_1_26_1","volume-title":"Proceedings of ICML'2008","author":"Collobert R.","unstructured":"Collobert, R. and Weston, J. A unified architecture for natural language processing: Deep neural networks with multitask learning. In Proceedings of ICML'2008."},{"key":"e_1_2_1_27_1","volume-title":"Advances in Neural Information Processing Systems 32","author":"Conneau A.","year":"2019","unstructured":"Conneau, A. and Lample, G. Cross-lingual language model pretraining. Advances in Neural Information Processing Systems 32, 2019. H. Wallach et al., eds. 7059--7069. Curran Associates, Inc.; http:\/\/papers.nips.cc\/paper\/8928-cross-lingual-language-model-pretraining.pdf."},{"key":"e_1_2_1_28_1","first-page":"1","article-title":"Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition","volume":"20","author":"Dahl G.","year":"2011","unstructured":"Dahl, G., Yu, D., Deng, L., and Acero, A. Context-dependent pre-trained deep neural networks for large-vocabulary speech recognition. IEEE Trans. Audio, Speech, and Language Processing 20, 1 (2011), 30--42.","journal-title":"IEEE Trans. Audio, Speech, and Language Processing"},{"key":"e_1_2_1_29_1","volume-title":"Theoretical Neuroscience","author":"Dayan P.","year":"2001","unstructured":"Dayan, P. and Abbott, L. Theoretical Neuroscience. The MIT Press, 2001."},{"key":"e_1_2_1_30_1","volume-title":"What is consciousness, and could machines have it? Science 358, 6362","author":"Dehaene S.","year":"2017","unstructured":"Dehaene, S., Lau, H., and Kouider, S. What is consciousness, and could machines have it? Science 358, 6362 (2017, 486--492."},{"key":"e_1_2_1_31_1","volume-title":"Proceedings of 2009 IEEE Conf. Computer Vision and Pattern Recognition, 248--255","author":"Deng J.","unstructured":"Deng, J., Dong, W., Socher, R., Li, L., Li, K., and Fei-Fei, L. ImageNet: A large-scale hierarchical image database. In Proceedings of 2009 IEEE Conf. Computer Vision and Pattern Recognition, 248--255."},{"key":"e_1_2_1_32_1","volume-title":"Proceedings of ACL'2019; arXiv:1810","author":"Devlin J.","unstructured":"Devlin, J., Chang, M., Lee, K., and Toutanova, K. Bert: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of ACL'2019; arXiv:1810.04805."},{"key":"e_1_2_1_33_1","volume-title":"Model-agnostic meta-learning for fast adaptation of deep networks","author":"Finn C.","year":"2017","unstructured":"Finn, C., Abbeel, P., and Levine, S. Model-agnostic meta-learning for fast adaptation of deep networks, 2017; arXiv:1703.03400."},{"key":"e_1_2_1_34_1","volume-title":"Proceedings of Intern. Conf. Machine Learning","author":"Ganin Y","year":"2015","unstructured":"Ganin, Y and Lempitsky, V. Unsupervised domain adaptation by backpropagation. In Proceedings of Intern. Conf. Machine Learning, 2015, 1180--1189."},{"key":"e_1_2_1_35_1","volume-title":"Proceedings of AISTATS'2011","author":"Glorot X.","unstructured":"Glorot, X., Bordes, A., and Bengio, Y. Deep sparse rectifier neural networks. In Proceedings of AISTATS'2011."},{"key":"e_1_2_1_36_1","first-page":"26804","article-title":"Generative adversarial nets","volume":"2672","author":"Goodfellow I.","year":"2014","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. Generative adversarial nets. In Advances in Neural Information Processing Systems, 2014, 2672--26804.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.111.1.3"},{"key":"e_1_2_1_38_1","volume-title":"Recurrent independent mechanisms","author":"Goyal A.","year":"2019","unstructured":"Goyal, A., Lamb, A., Hoffmann, J., Sodhani, S., Levine, S., Bengio, Y., and Sch\u00f6lkopf, B. Recurrent independent mechanisms, 2019; arXiv:1909.10893."},{"key":"e_1_2_1_39_1","volume-title":"Generating sequences with recurrent neural networks","author":"Graves A.","year":"2013","unstructured":"Graves, A. Generating sequences with recurrent neural networks, 2013; arXiv:1308.0850."},{"key":"e_1_2_1_40_1","volume-title":"et al. Bootstrap your own latent: A new approach to self-supervised learning","author":"Grill J-B","year":"2020","unstructured":"Grill, J-B. et al. Bootstrap your own latent: A new approach to self-supervised learning, 2020; aeXiv:2006.07733."},{"key":"e_1_2_1_41_1","volume-title":"Proceedings of the 13th Intern. Conf. Artificial Intelligence and Statistics","author":"Gutmann M.","year":"2010","unstructured":"Gutmann, M. and Hyv\u00e4rinen, A. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In Proceedings of the 13th Intern. Conf. Artificial Intelligence and Statistics, 2010, 297--304."},{"key":"e_1_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_2_1_43_1","volume-title":"Proceedings of CVPR'2016","author":"He K.","unstructured":"He, K., Zhang, X., Ren, S., and Sun, J. Deep residual learning for image recognition. In Proceedings of CVPR'2016, 770--778."},{"key":"e_1_2_1_44_1","volume-title":"Proceedings of the 7th Intern. Joint Conf. Artificial Intelligence 2","author":"Hinton G.","year":"1981","unstructured":"Hinton, G. A parallel computation that assigns canonical object-based frames of reference. In Proceedings of the 7th Intern. Joint Conf. Artificial Intelligence 2, 1981, 683--685."},{"key":"e_1_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(90)90002-H"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21735-7_6"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2006.18.7.1527"},{"key":"e_1_2_1_49_1","first-page":"186","article-title":"Using fast weights to deblur old memories. In Proceedings of the 9th Annual Conf","volume":"177","author":"Hinton G.","year":"1987","unstructured":"Hinton, G. and Plaut, D. Using fast weights to deblur old memories. In Proceedings of the 9th Annual Conf. Cognitive Science Society, 1987, 177--186.","journal-title":"Cognitive Science Society"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"e_1_2_1_51_1","volume-title":"Proceedings of NeurIPS'2012; arXiv:1207","author":"Hinton G.","unstructured":"Hinton, G., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R. Improving neural networks by preventing co-adaptation of feature detectors. In Proceedings of NeurIPS'2012; arXiv:1207.0580."},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_2_1_53_1","volume-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"Ioffe S.","year":"2015","unstructured":"Ioffe, S. and Szegedy, C. Batch normalization: Accelerating deep network training by reducing internal covariate shift. 2015."},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459469"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"e_1_2_1_56_1","unstructured":"Kahneman D. Thinking Fast and Slow. Macmillan 2011."},{"key":"e_1_2_1_57_1","volume-title":"Learning neural causal models from unknown interventions","author":"Ke N.","year":"2019","unstructured":"Ke, N., Bilaniuk, O., Goyal, A., Bauer, S., Larochelle, H., Pal, C., and Bengio, Y. Learning neural causal models from unknown interventions, 2019; arXiv:1910.01075."},{"key":"e_1_2_1_58_1","volume-title":"Proceedings of the Intern. Conf. Learning Representations","author":"Kingma D.","year":"2014","unstructured":"Kingma, D. and Welling, M. Auto-encoding variational bayes. In Proceedings of the Intern. Conf. Learning Representations, 2014."},{"key":"e_1_2_1_59_1","first-page":"15522","article-title":"Stacked capsule autoencoders","volume":"15512","author":"Kosiorek A.","year":"2019","unstructured":"Kosiorek, A., Sabour, S., Teh, Y., and Hinton, G. Stacked capsule autoencoders. Advances in Neural Information Processing Systems, 2019, 15512--15522.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_60_1","volume-title":"Proceedings of NIPS'2012","author":"Krizhevsky A.","unstructured":"Krizhevsky, A., Sutskever, I., and Hinton, G. ImageNet classification with deep convolutional neural networks. In Proceedings of NIPS'2012."},{"key":"e_1_2_1_61_1","first-page":"40","article-title":"Building machines that learn and think like people","author":"Lake B.","year":"2017","unstructured":"Lake, B., Ullman, T., Tenenbaum, J., and Gershman, S. Building machines that learn and think like people. Behavioral and Brain Sciences 40 (2017).","journal-title":"Behavioral and Brain Sciences"},{"key":"e_1_2_1_62_1","volume-title":"Proceedings of ICLR'2020; arXiv:1912","author":"Lample G.","unstructured":"Lample, G. and Charton, F. Deep learning for symbolic mathematics. In Proceedings of ICLR'2020; arXiv:1912.01412."},{"key":"e_1_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.541"},{"key":"e_1_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.14"},{"key":"e_1_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"e_1_2_1_68_1","volume-title":"Proceedings of NIPS Workshop on Deep Learning for Speech Recognition and Related Applications.","author":"Mohamed A.","year":"2009","unstructured":"Mohamed, A., Dahl, G., and Hinton, G. Deep belief networks for phone recognition. In Proceedings of NIPS Workshop on Deep Learning for Speech Recognition and Related Applications. (Vancouver, Canada, 2009)."},{"key":"e_1_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1990.116058"},{"key":"e_1_2_1_70_1","volume-title":"Proceedings of the ICML'2010","author":"Nair V.","unstructured":"Nair, V. and Hinton, G. Rectified linear units improve restricted Boltzmann machines. In Proceedings of the ICML'2010."},{"key":"e_1_2_1_71_1","volume-title":"Automatic differentiation in pytorch","author":"Paszke A.","year":"2017","unstructured":"Paszke, A., et al. Automatic differentiation in pytorch. 2017."},{"key":"e_1_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.279192"},{"key":"e_1_2_1_73_1","volume-title":"Recipes for building an open domain chatbot","author":"Roller S.","year":"2020","unstructured":"Roller, S., et al. Recipes for building an open domain chatbot, 2020; arXiv:2004.13637."},{"key":"e_1_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_2_1_75_1","volume-title":"Tech","author":"Schmidhuber J.","year":"1987","unstructured":"Schmidhuber, J. Evolutionary principles in self-referential learning. Diploma thesis, Institut f. Informatik, Tech.Univ. Munich, 1987."},{"key":"e_1_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.3629243"},{"key":"e_1_2_1_77_1","volume-title":"Mastering the game of go with deep neural networks and tree search. Nature 529, 7587","author":"Silver D.","year":"2016","unstructured":"Silver, D., et al. Mastering the game of go with deep neural networks and tree search. Nature 529, 7587 (2016), 484."},{"key":"e_1_2_1_78_1","first-page":"2440","article-title":"End-to-end memory networks","volume":"28","author":"Sukhbaatar S.","year":"2015","unstructured":"Sukhbaatar, S., Szlam, A., Weston, J., and Fergus, R. End-to-end memory networks. Advances in Neural Information Processing Systems 28, 2015, 2440--2448. C. Cortes et al., eds. Curran Associates, Inc.; http:\/\/papers.nips.cc\/paper\/5846-end-to-end-memory-networks.pdf.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_79_1","volume-title":"Proceedings of ICLR'2014; arXiv:1312","author":"Szegedy C.","unstructured":"Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., and Fergus, R. Intriguing properties of neural networks. In Proceedings of ICLR'2014; arXiv:1312.6199."},{"key":"e_1_2_1_80_1","volume-title":"Proceedings of CVPR'2015","author":"Taigman Y.","unstructured":"Taigman, Y., Yang, M., Ranzato, M., and Wolf, L. Web-scale training for face identification. In Proceedings of CVPR'2015, 2746--2754."},{"key":"e_1_2_1_81_1","volume-title":"Proceedings of NIPS'1995","author":"Thrun S.","unstructured":"Thrun, S. Is learning the n-th thing any easier than learning the first? In Proceedings of NIPS'1995. MIT Press, Cambridge, MA, 640--646."},{"key":"e_1_2_1_82_1","doi-asserted-by":"publisher","DOI":"10.1162\/08997660260293319"},{"key":"e_1_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1016\/0166-2236(83)90167-4"},{"key":"e_1_2_1_84_1","volume-title":"Relational neural expectation maximization: Unsupervised discovery of objects and their interactions","author":"van Steenkiste S.","year":"2018","unstructured":"van Steenkiste, S., Chang, M., Greff, K., and Schmidhuber, J. Relational neural expectation maximization: Unsupervised discovery of objects and their interactions, 2018; arXiv:1802.10353."},{"key":"e_1_2_1_85_1","first-page":"6008","article-title":"Attention is all you need","volume":"5998","author":"Vaswani A.","year":"2017","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A., Kaiser, T., and Polosukhin, I. Attention is all you need. Advances in Neural Information Processing Systems, 2017, 5998--6008.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_1_86_1","volume-title":"Relational deep reinforcement learning","author":"Zambaldi V.","year":"2018","unstructured":"Zambaldi, V., et al. Relational deep reinforcement learning, 2018; arXiv:1806.01830."},{"key":"e_1_2_1_87_1","volume-title":"Proceedings of the 2017 IEEE Intern. Conf. on Computer Vision, 2223--2232","author":"Zhu J-Y.","unstructured":"Zhu, J-Y., Park, T., Isola, P., and Efros, A. Unpaired image-to-image translation using cycle-consistent adversarial networks. In Proceedings of the 2017 IEEE Intern. Conf. on Computer Vision, 2223--2232."}],"container-title":["Communications of the ACM"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3448250","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3448250","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:47:41Z","timestamp":1750193261000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3448250"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,21]]},"references-count":87,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["10.1145\/3448250"],"URL":"https:\/\/doi.org\/10.1145\/3448250","relation":{},"ISSN":["0001-0782","1557-7317"],"issn-type":[{"value":"0001-0782","type":"print"},{"value":"1557-7317","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,21]]},"assertion":[{"value":"2021-06-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}