机器推理的进展与展望

doi:10.16451/j.cnki.issn1003-6059.202101001

摘要
图/表
参考文献(0)
相关文章 (13)

全文: PDF (1218 KB) HTML (1 KB)
输出: BibTeX | EndNote (RIS)

摘要

机器学习算法的发展仍受到泛化能力较弱、鲁棒性较差、缺乏可解释性等问题的限制.文中介绍机器推理,说明推理对于机器学习人的知识和逻辑、理解和解释世界的重要作用.首先分析人类大脑推理机制,从认知地图、神经元和奖赏回路,扩展到受脑启发的直觉推理、神经网络和强化学习.进而总结机器推理的方式及其相互关联的现状、进展及挑战,具体包括直觉推理、常识推理、因果推理和关系推理等.最后展望机器推理的应用前景与未来的研究方向.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	丁梦远
	兰旭光
	彭茹
	郑南宁

关键词 ：人工智能, 机器推理, 直觉推理, 因果推理

Abstract：

The development of machine learning algorithms are limited by the problems, such as weak generalization ability, poor robustness and lack of interpretability. In this paper, the important role of reasoning for machine learning human knowledge and logic, understanding and interpreting the world is illustrated. Firstly, the reasoning mechanism of the human brain is studied from cognitive maps, neurons and reward circuits, to brain-inspired intuitive reasoning, neural networks and reinforcement learning. Then, the current situation, progress and challenges of machine reasoning methods and their interrelationships are summarized, including intuitive reasoning, commonsense reasoning, causal reasoning and relational reasoning. Finally, the application prospects and future research directions of machine reasoning are analyzed.

Key words： Artificial Intelligence Machine Reasoning Intuitive Reasoning Causal Reasoning

收稿日期: 2020-12-27

ZTFLH:

TP 391

基金资助:

国家自然科学基金重点项目(No.91748208)、陕西省重点研发计划项目(No.2018ZDCXLGY0607)、国家自然科学基金面上项目(No.61973246)、教育部规划项目资助

通讯作者: 兰旭光,博士,教授,主要研究方向为计算机视觉、机器学习.E-mail:xglan@mail.xjtu.edu.cn.

作者简介: 丁梦远,博士研究生,主要研究方向为计算机视觉推理.E-mail:dmyadicul@qq.com.
彭茹,博士研究生,主要研究方向为基于计算机视觉的场景理解.E-mail:nancypt@mail.xjtu.edu.cn.
郑南宁,博士,教授,主要研究方向为计算机视觉、模式识别.E-mail:nnzheng@mail.xjtu.edu.cn.

引用本文:

丁梦远, 兰旭光, 彭茹, 郑南宁. 机器推理的进展与展望[J]. 模式识别与人工智能, 2021, 34(1): 1-13. DING Mengyuan, LAN Xuguang, PENG Ru, ZHENG Nanning. Progress and Prospect of Machine Reasoning. , 2021, 34(1): 1-13.

链接本文:

http://manu46.magtech.com.cn/Jweb_prai/CN/10.16451/j.cnki.issn1003-6059.202101001 或 http://manu46.magtech.com.cn/Jweb_prai/CN/Y2021/V34/I1/1

[1] SHANNON C E. Programming a Computer for Playing Chess // LEVY D, ed. Computer Chess Compendium. Berlin, Germany: Springer, 1988: 2-13.
[2] COOPER S B, VAN LEEUWEN J. Solvable and Unsolvable Pro-blems. London, UK: Penguin Books, 1954.
[3] MCCARTHY J, MINSKY M L, ROCHESTER N, et al. A Proposal for the Dartmouth Summer Research Project on Artificial Intelligence[C/OL]. [2020-12-12]. http://jmc.stanford.edu/articles/dartmouth/dartmouth.pdf.
[4] BOBROW D G. Natural Language Input for a Computer Problem Solving System[C/OL]. [2020-12-12]. http://hdl.handle.net/1721.1/5922.
[5] WEIZENBAUM J. ELIZA-A Computer Program for the Study of Na-tural Language Communication between Man and Machine. Communications of the ACM, 1966, 9(1): 36-45.
[6] BUCHANAN B, SUTHERLAND G, FEIGENBAUM E A. Heuristic DENDRAL: A Program for Generating Explanatory Hypotheses[C/OL]. [2020-12-12]. https://stacks.stanford.edu/file/druid:pf885vk0607/pf885vk0607.pdf.
[7] DAVIS R. Use of Meta Level Knowledge in the Construction and Maintenance of Large Knowledge Bases. Ph.D. Dissertation. Stanford, USA: Stanford University, 1976.
[8] MCDERMOTT D, DOYLE J. Non-monotonic Logic I. Artificial Intelligence, 1980, 13(1/2): 41-72.
[9] BROOKS R. A Robust Layered Control System for a Mobile Robot. IEEE Journal on Robotics and Automation, 1986, 2(1): 14-23.
[10] OAD Map[EB/OL]. [2020-12-12]. https://www.emse.fr/~beaune/websem/SWRoadmapLee.pdf.
[11] LECUN Y, BENGIO Y, HINTON G. Deep Learning. Nature, 2015, 521(7553): 436-444.
[12] TANG J, ZHANG J, YAO L M, et al. Arnetminer: Extraction and Mining of Academic Social Networks // Proc of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2008: 990-998.
[13] WUEST T, WEIMER D, IRGENS C, et al. Machine Learning in Manufacturing: Advantages, Challenges, and Applications. Production and Manufacturing Research, 2016, 4(1): 23-45.
[14] CAMPBELL M, HOANE JR A J, HSU F H. Deep Blue. Artificial intelligence, 2002, 134(1/2): 57-83.
[15] MARKOFF J. Computer Wins on ‘Jeopardy!’:Trivial, It′s Not[EB/OL]. [2020-12-12].https://www.nytimes.com/2011/02/17/science/17jeopardy-watson.html.
[16] SILVER D, HUANG A, MADDISON C J, et al. Mastering the Game of Go with Deep Neural Networks and Tree Search. Nature, 2016, 529(7587): 484-489.
[17] BERNER C, BROCKMAN G, CHAN B, et al. Dota 2 with Large Scale Deep Reinforcement Learning[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1912.06680.pdf.
[18] SHAW J, RUDZICZ F, JAMIESON T, et al. Artificial Intelligence and the Implementation Challenge. Journal of Medical Internet Research, 2019, 21(7). DOI: 10.2196/13659.
[19] PEARL J, MACKENZIE D. The Book of Why: The New Science of Cause and Effect. New York, USA: Basic Books, 2018.
[20] KOMPRIDIS N. So We Need Something Else for Reason to Mean. International Journal of Philosophical Studies, 2000, 8(3): 271-295.
[21] GOSWAMI U. Cognitive Development: The Learning Brain. International Journal of Language and Communication Disorders, 2010, 45(2). DOI: 10.3109/13682820903211091.
[22] FURBACH U, HÖLLDOBLER S, RAGNI M, et al. Cognitive Rea-soning: A Personal View. KI-Künstliche Intelligenz, 2019, 33(3): 209-217.
[23] BEATH C, BECERRA-FERNANDEZ I, ROSS J, et al. Finding Value in the Information Explosion. MIT Sloan Management Review, 2012, 53(4): 18-20.
[24] DE RAEDT L, GUNS T, NIJSSEN S. Constraint Programming for Data Mining and Machine Learning // Proc of the 24th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2010, III: 1671-1675.
[25] WANG Q, MAO Z D, WANG B, et al. Knowledge Graph Embe-dding: A Survey of Approaches and Applications. IEEE Transactions on Knowledge and Data Engineering, 2017, 29(12): 2724-2743.
[26] CHOWDHARY K R. Natural Language Processing // CHOWDH-ARY K R, ed. Fundamentals of Artificial Intelligence. Berlin, Germany: Springer, 2020: 603-649.
[27] HAGMANN P, CAMMOUN L, GIGANDET X, et al. Mapping the Structural Core of Human Cerebral Cortex. PLoS Biology, 2008, 6(7). DOI: 10.1371/journal.pbio.0060159.
[28] MACNEILAGE P F, ROGERS L J, VALLORTIGARA G. Origins of the Left and Right Brain. Scientific American, 2009, 301(1): 60-67.
[29] BRESSLER S L, MENON V. Large-Scale Brain Networks in Cognition: Emerging Methods and Principles. Trends in Cognitive Sciences, 2010, 14(6): 277-290.
[30] EVANS J S B T. How Many Dual-Process Theories Do We Need? One, Two, or Many? // EVANS J S B T, FRANKISH K, eds. In Two Minds: Dual Processes and Beyond. Oxford, UK: Oxford University Press, 2009: 33-54.
[31] KUO W J, SJÖSTRÖM T, CHEN Y P, et al. Intuition and Deliberation: Two Systems for Strategizing in the Brain. Science, 2009, 324(5926): 519-522.
[32] MÜLLER K, FAEH C, DIEDERICH F. Fluorine in Pharmaceuticals: Looking beyond Intuition. Science, 2007, 317(5846): 1881-1886.
[33] DEWALL C N, BAUMEISTER R F, MASICAMPO E J. Evidence That Logical Reasoning Depends on Conscious Processing. Consciousness and Cognition, 2008, 17(3): 628-645.
[34] WHARTON C M, GRAFMAN J. Deductive Reasoning and the Brain. Trends in Cognitive Sciences, 1998: 54-59.
[35] STEPHENS R G, DUNN J C, HAYES B K, et al. A Test of Two Processes: The Effect of Training on Deductive and Inductive Reasoning. Cognition, 2020, 199. DOI: 10.1016/j.cognition.2020.104223.
[36] STENNING K, OBERLANDER J. A Cognitive Theory of Graphical and Linguistic Reasoning: Logic and Implementation. Cognitive science, 1995, 19(1): 97-140.
[37] O'KEEFE J, NADEL L. The Hippocampus as a Cognitive Map. Oxford, UK: Clarendon Press, 1978.
[38] STERNBERG R J, DAVIDSON J E. Insight in the Gifted. Educational Psychologist, 1983, 18(1): 51-57.
[39] SALVI C, BRICOLO E, KOUNIOS J, et al. Insight Solutions Are Correct More Often Than Analytic Solutions. Thinking and Reaso-ning, 2016, 22(4): 443-460.
[40] ZHENG N N, LIU Z Y, REN P J, et al. Hybrid-Augmented Inte-lligence: Collaboration and Cognition. Frontiers of Information Technology and Electronic Engineering, 2017, 18(2): 153-179.
[41] CREAMER M, BURGESS P, PATTISON P. Reaction to Trauma: A Cognitive Processing Model. Journal of Abnormal Psychology, 1992, 101(3): 452-459.
[42] HAGAN M T, DEMUTH H B, BEALE M H, et al. Neural Network Design. Boston, USA: PWS Publishing, 2014.
[43] WISE R A, BOZARTH M A. Brain Reward Circuitry: Four Circuit Elements “Wired” in Apparent Series. Brain Research Bulletin, 1984, 12(2): 203-208.
[44] PADMANABHAN A, GEIER C F, ORDAZ S J, et al. Develo-pmental Changes in Brain Function Underlying the Influence of Reward Processing on Inhibitory Control. Developmental Cognitive Neuroscience, 2011, 1(4): 517-529.
[45] SUTTON R S, BARTO A G. Reinforcement Learning: An Introduction. Cambridge, USA: The MIT Press, 2018.
[46] PRESTON J, MARK B. Views into the Chinese Room: New Essays on Searle and Artificial Intelligence. Oxford, UK: Oxford University Press, 2002.
[47] LAVIE N, HIRST A, DE FOCKERTJ W, et al. Load Theory of Selective Attention and Cognitive Control. Journal of Experimental Psychology(General), 2004, 133(3): 339-354.
[48] ALISEDA A. Abductive Reasoning: Challenges Ahead. THEORIA, 2007, 22(3): 261-270.
[49] PAN Y H. Multiple Knowledge Representation of Artificial Intelligence. Engineering, 2020, 6(3): 216-217.
[50] PAN Y H. On Visual Knowledge. Frontiers of Information Techno-logy and Electronic Engineering, 2019, 20(8): 1021-1025.
[51] DAVIS E, MARCUS G. Commonsense Reasoning and Commonsense Knowledge in Artificial Intelligence. Communications of the ACM, 2015, 58(9): 92-103.
[52] LU R, XUE F, ZHOU M H, et al. Occlusion-Shared and Feature-Separated Network for Occlusion Relationship Reasoning // Proc of the IEEE International Conference on Computer Vision. Washington, USA: IEEE, 2019: 10343-10352.
[53] JANIS I L, MANN L. Decision Making: A Psychological Analysis of Conflict, Choice, and Commitment. New York, USA: Free Press, 1977.
[54] BROWNE C B, POWLEY E, WHITEHOUSE D, et al. A Survey of Monte Carlo Tree Search Methods. IEEE Transactions on Computational Intelligence and AI in Games, 2012, 4(1): 1-43.
[55] SILVER D, HUBERT T, SCHRITTWIESER J, et al. Mastering Chess and Shogi by Self-play with a General Reinforcement Lear-ning Algorithm[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1712.01815.pdf.
[56] SCHRITTWIESER J, ANTONOGLOU I, HUBERT T, et al. Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model. Nature, 2020, 588(5839): 604-609.
[57] MCCARTHY J. An Everywhere Continuous Nowhere Differentiable Function. The American Mathematical Monthly, 1953, 60(10): 709.
[58] BENTIVOGLI L, DAGAN I, MAGNINI B. The Recognizing Textual Entailment Challenges: Datasets and Methodologies // IDE N, PUSTEJOVSKY J, eds. Handbook of Linguistic Annotation. Berlin, Germany: Springer, 2017: 1119-1147.
[59] ROEMMELE M, BEJAN C A, GORDON A S. Choice of Plausible Alternatives: An Evaluation of Commonsense Causal Reasoning // Proc of the AAAI Spring Symposium on Logical Formalizations of Commonsense Reasoning. Palo Alto, USA: AAAI Press, 2011: 90-95.
[60] MOSTAFAZADEH N, ROTH M, LOUIS A, et al. LSDSEM 2017 Shared Task: The Story Cloze Test // Proc of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics. Stroudsburg, USA: ACL, 2017: 46-51.
[61] STORKS S, GAO Q Z, CHAI J Y. Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1904.01172.pdf.
[62] LEVESQUE H J. The Winograd Schema Challenge[C/OL]. [2020-12-12]. http://www.cs.toronto.edu/~hector/Papers/winograd.pdf.
[63] OSTERMANN S, MODI A, ROTH M, et al. Mcscript: A Novel Dataset for Assessing Machine Comprehension Using Script Know-ledge[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1803.05223.pdf.
[64] TALMOR A, HERZIG J, LOURIE N, et al. CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1811.00937.pdf.
[65] BOWMAN S R, ANGELI G, POTTS C, et al. A Large Annotated Corpus for Learning Natural Language Inference[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1508.05326.pdf.
[66] KHOT T, SABHARWAL A, CLARK P. SciTaiL: A Textual Entailment Dataset from Science Question Answering // Proc of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto, USA:AAAI Press, 2018: 41-42.
[67] GORDON A S. Commonsense Interpretation of Triangle Behavior // Proc of the 13th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2016: 3719-3725.
[68] ZHANG S, RUDINGER R, DUH K, et al. Ordinal Common-Sense Inference. Transactions of the Association for Computational Linguistics, 2017, 5: 379-395.
[69] RASHKIN H, BOSSELUT A, SAP M, et al. Modeling Naive Psychology of Characters in Simple Commonsense Stories // Proc of the 56th Annual Meeting of the Association for Computational Linguistics(Long Papers). Stroudsburg, USA: ACL, 2018: 2289-2299.
[70] RASHKIN H, SAP M, ALLAWAY E, et al. Event2mind: Commonsense Inference on Events, Intents, and Reactions[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1805.06939.pdf.
[71] WANG A, SINGH A, MICHAEL J, et al. GLUE: A Multi-task Benchmark and Analysis Platform for Natural Language Understanding[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1804.07461.pdf.
[72] BOLT R A. “Put-That-There” Voice and Gesture at the Graphics Interface. ACM SIGGRAPH Computer Graphics, 1980, 14(3): 262-270.
[73] NYGA D, BEETZ M. Cloud-Based Probabilistic Knowledge Ser-vices for Instruction Interpretation // BICCHI A, BURGARD W, eds. Robotics Research. Berlin, Germany: Springer, 2018: 649-664.
[74] SAXENA A, JAIN A, SENER O, et al. RoboBrain: Large-Scale Knowledge Engine for Robots[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1412.0691.pdf.
[75] WANG T, HUANG J Q, ZHANG H W, et al. Visual Commonsense R-CNN // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 10760-10770.
[76] ZAREIAN A, WANG Z C, YOU H X, et al. Learning Visual Commonsense for Robust Scene Graph Generation // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2020: 642-657.
[77] ADITYA S, YANG Y Z, BARAL C, et al. Image Understanding Using Vision and Reasoning through Scene Description Graph. Computer Vision and Image Understanding, 2018, 173: 33-45.
[78] ZELLERS R, BISK Y, FARHADI A, et al. From Recognition to Cognition: Visual Commonsense Reasoning // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 6720-6731.
[79] HOU J Y, WU X X, ZHANG X X, et al. Joint Commonsense and Relation Reasoning for Image and Video Captioning // Proc of the AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2020: 10973-10980.
[80] HENDRICKS L A, BURNS K, SAENKO K, et al. Women Also Snowboard: Overcoming Bias in Captioning Models // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 793-811.
[81] KUANG K, LI L, GENG Z, et al. Causal Inference. Engineering, 2020, 6(3): 253-263.
[82] KUANG K, CUI P, ATHEY S, et al. Stable Prediction across Unknown Environments // Proc of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, USA: ACM, 2018: 1617-1626.
[83] LUO Z Y, SHA Y C, ZHU K Q, et al. Commonsense Causal Reasoning between Short Texts // Proc of the 15th International Conference on Principles of Knowledge Representation and Reasoning. New York, USA: ACM, 2016: 421-431.
[84] HAVASI C, SPEER R, ARNOLD K, et al. Open Mind Common Sense: Crowd-Sourcing for Common Sense // Proc of the 2nd AAAI Conference on Collaboratively-Built Knowledge Sources and Artificial Intelligence. Palo Alto, USA: AAAI Press, 2010: 53.
[85] GORDON A S, BEJAN C A, SAGAE K. Commonsense Causal Reasoning Using Millions of Personal Stories // Proc of the 25th AAAI Conference on Artificial Intelligence. Palo Alto, USA: AAAI Press, 2011: 1180-1185.
[86] VERMA S, DICKERSON J, HINES K. Counterfactual Explanations for Machine Learning: A Review[C/OL]. [2020-12-12]. https://arxiv.org/pdf/2010.10596.pdf.
[87] BESSERVE M, MEHRJOU A, SUN R, et al. Counterfactuals Uncover the Modular Structure of Deep Generative Models[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1812.03253.pdf.
[88] KAUSHIK D, HOVY E, LIPTON Z C. Learning the Difference That Makes a Difference with Counterfactually-Augmented Data[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1909.12434v1.pdf.
[89] LOPEZ-PAZ D, NISHIHARA R, CHINTALA S, et al. Discovering Causal Signals in Images // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 58-66.
[90] QI J X, NIU Y L, HUANG J Q, et al. Two Causal Principles for Improving Visual Dialog // Proc of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 10860-10869.
[91] TANG K H, NIU Y L, HUANG J Q, et al. Unbiased Scene Graph Generation from Biased Training // Proc of the IEEE/CVF Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2020: 3716-3725.
[92] YI K X, GAN C, LI Y Z, et al. CLEVRER: Collision Events for Video Representation and Reasoning[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1910.01442.pdf.
[93] DASGUPTA I, WANG J, CHIAPPA S, et al. Causal Reasoning from Meta-Reinforcement Learning[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1901.08162v1.pdf.
[94] REHDER B. A Causal-Model Theory of Conceptual Representation and Categorization. Journal of Experimental Psychology: Learning, Memory, and Cognition, 2003, 29(6): 1141-1159.
[95] GUPTA A, DAVIS L S. Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2008: 16-29.
[96] JOHNSON J, HARIHARAN B, VAN DER MAATEN L, et al. CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2017: 2901-2910.
[97] YAO B P, LI F F. Grouplet: A Structured Image Representation for Recognizing Human and Object Interactions // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2010: 9-16.
[98] SADEGHI M A, FARHADI A. Recognition Using Visual Phrases // Proc of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2011: 1745-1752.
[99] FANG H, GUPTA S, IANDOLA F, et al. From Captions to Visual Concepts and Back // Proc of the IEEE Computer Society Confe-rence on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2015: 1473-1482.
[100] LU C W, KRISHNA R, BERNSTEIN M, et al. Visual Relationship Detection with Language Priors // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2016: 852-869.
[101] VELICˇKOVIC ＇P, CUCURULL G, CASANOVA A, et al. Graph Attention Networks[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1904.05811.pdf.
[102] PEREZ E, DE VRIES H, STRUB F, et al. Learning Visual Reasoning without Strong Priors[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1707.03017.pdf.
[103] ZHOU B L, ANDONIAN A, OLIVA A, et al. Temporal Relational Reasoning in Videos // Proc of the European Conference on Computer Vision. Berlin, Germany: Springer, 2018: 803-818.
[104] WATTERS N, ZORAN D, WEBER T, et al. Visual Interaction Networks: Learning a Physics Simulator from Video // GUYON I, LUXBURG U V, BENGIO S, et al., eds. Advances in Neural Information Processing Systems 30. Cambridge, USA: The MIT Press, 2017: 4539-4547.
[105] VAN STEENKISTE S, CHANG M, GREFF K, et al. Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and Their Interactions[C/OL]. [2020-12-12]. https://arxiv.org/pdf/1802.10353.pdf.
[106] CADENE R, BEN-YOUNES H, CORD M, et al. MUREL: Multimodal Relational Reasoning for Visual Question Answering // Proc of the IEEE Conference on Computer Vision and Pattern Recognition. Washington, USA: IEEE, 2019: 1989-1998.
[107] STONE P, BROOKS R, BRYNJOLFSSON E, et al. Artificial Intelligence and Life in 2030: One Hundred Year Study on Artificial Intelligence[C/OL]. [2020-12-12]. https://ai100.stanford.edu/sites/g/files/sbiybj9861/f/ai_100_report_0831fnl.pdf.