混合-增强智能：协作与认知

Abstract

人工智能追求的长期目标是使机器能像人一样学习和思考。由于人类面临的许多问题具有不确定性、脆弱性和开放性，任何智能程度的机器都无法完全取代人类，这就需要将人的作用或人的认知模型引入到人工智能系统中，形成混合-增强智能的形态，这种形态是人工智能或机器智能的可行的、重要的成长模式。混合-增强智能可以分为两类基本形式：一类是人在回路的人机协同混合增强智能，另一类是将认知模型嵌入机器学习系统中，形成基于认知计算的混合智能。本文讨论人机协同的混合-增强智能的基本框架，以及基于认知计算的混合-增强智能的基本要素：直觉推理与因果模型、记忆和知识演化；特别论述了直觉推理在复杂问题求解中的作用和基本原理，以及基于记忆与推理的视觉场景理解的认知学习网络；阐述了竞争-对抗式认知学习方法，并讨论了其在自动驾驶方面的应用；最后给出混合-增强智能在相关领域的典型应用。

Keywords

人-机协同 / 混合增强智能 / 认知计算 / 直觉推理 / 因果模型 / 认知映射 / 视觉场景理解 / 自主驾驶汽车

References

[1] Ando , R.K., 2007. Biocreative II gene mention tagging system at IBM Watson. Proc. 2nd BioCreative Challenge Evaluation Workshop, p.101–103.

[2] Ando , R.K., Dredze , M., Zhang , T., 2005. Trec 2005 genomics track experiments at IBM Watson. 14th Text REtrieval Conf., p.1–10.

[3] Atif , Y., Mathew , S.S., 2015. Building a smart campus to support ubiquitous learning. J. Amb. Intell. Human. Comput., 6(2):1–16.

[4] Ball , M.O., Chen , C.Y., Hoffman , R., , 2001. Collaborative decision making in air traffic management: current and future research directions.In: Bianco, L., Dell’Olmo, P., Odoni, A.R. (Eds.), New Concepts and Methods in Air Traffic Management. Springer Berlin Heidelberg, Berlin, Germany, p.17–30.

[5] Barnes , M.J., Chen , J.Y.C., Jentsch , F., , 2013. An overview of humans and autonomy for military environments: safety, types of autonomy, agents, and user interfaces. Proc. 10th Int. Conf. on Engineering Psychology and Cognitive Ergonomics: Applications and Services, p.243–252.

[6] Boman , I.L., Bartfai , A., 2015. The first step in using a robot in brain injury rehabilitation: patients’ and health-care professionals’ perspective.Disab. Rehab. Assist. Technol., 10(5):365–370.

[7] Bradley , A.P., 1997. The use of the area under the ROC curve in the evaluation of machine learning algorithms.Patt. Recogn., 30(7):1145–1159.

[8] Browne , C.B., Powley , E., Whitehouse , D., , 2012. A survey of Monte Carlo tree search methods.IEEE Trans. Comput. Intell. AI Games, 4(1):1–43.

[9] Campbell , M., Hoane , A.J.Jr., Hsu , F.H., 2002. Deep Blue.Artif. Intell., 134(1-2):57–83.

[10] Chen , D., Yuan , Z., Hua , G., , 2016. Multi-timescale collaborative tracking.IEEE Trans. Patt. Anal. Mach. Intell., 39(1):141–155.

[11] Chen , Y., Argentinis , J.D.E., Weber , G., 2016. IBM Watson: how cognitive computing can be applied to big data challenges in life sciences research.Clin. Therap., 38(4):688–701.

[12] Cimbala , S.J., 2012. Artificial Intelligence and National Security. Lexington Books, Lanham, USA.

[13] Denton , E.L., Chintala , S., Fergus , R., , 2015. Deep generative image models using a Laplacian pyramid of adversarial networks. Proc. 28th Int. Conf. on Neural Information Processing Systems, p.1486–1494.

[14] de Rocquigny , E., Nicolas , D., Stefano , T., 2008. Uncertainty in Industrial Practice: a Guide to Quantitative Uncertainty Management. John Wiley & Sons, Hoboken, USA.

[15] Dias , M.G., Harris , P., 1988. The effect of make-believe play on deductive reasoning.Br. J. Devel. Psychol., 6(3):207–221.

[16] Dounias , G., 2003. Hybrid computational intelligence in medicine. Proc. Workshop on Intelligent and Adaptive Systems in Medicine.

[17] Eakin , H., Luers , A.L., 2006. Assessing the vulnerability of social-environmental systems.Ann. Rev. Environ. Resourc., 31:1–477.

[18] Ferreira , F.J., Crispim , V.R., Silva , A.X., 2010. Detection of drugs and explosives using neutron computerized tomography and artificial intelligence techniques.Appl. Rad. Isot., 68(6):1012–1017.

[19] Fire , A., Zhu , S.C., 2016. Learning perceptual causality from video.ACM Trans. Intell. Syst. Technol., 7(2):1–22.

[20] Fischbein , H., 2002. Intuition in Science and Mathematics: an Educational Approach. Springer Science & Business Media, Berlin, Germany.

[21] Fjellheim , R., Bratvold , R.R., Herbert , M.C., 2008. CODIO- collaborative decisionmaking in integrated operations. Intelligent Energy Conf. and Exhibition, p.1–7.

[22] Fogel , D.B., 1995. Evolutionary Computation: Toward a New Philosophy of Machine Intelligence. Wiley-IEEE Press.

[23] Freyd , J.J., 1983. Representing the dynamics of a static form.Memory Cogn., 11(4):342–346.

[24] Funahashi , K.I., Nakamura , Y., 1993. Approximation of dynamic systems by continuous-time recurrent neural networks.Neur. Netw., 6(6):801–806.

[25] Gil , Y., Greaves , M., Hendler , J., , 2014. Amplify scientific discovery with artificial intelligence.Science, 346(6206):171–172.

[26] Gilbert , G.R., Beebe , M.K., 2010. United States Department of Defense Research in Robotic Unmanned Systems for Combat Casualty Care. Report No. RTO-MP-HFM-182, Fort Detrick, Frederick, USA.

[27] Goodfellow , I.J., Shlens , J., Szegedy , C., 2014a. Explaining and harnessing adversarial examples. ePrint Archive, arXiv:1412.6572.

[28] Goodfellow , I.J., Pougetabadie , J., Mirza , M., , 2014b. Generative adversarial nets. Advances in Neural Information Processing Systems, p.2672–2680.

[29] Graves , A., Mohamed , A.R., Hinton , G., 2013. Speech recognition with deep recurrent neural networks. IEEE Int. Conf. on Acoustics, Speech and Signal Processing, p.6645–6649.

[30] Graves , A., Wayne , G., Danihelka , I., 2014. Neural turing machines. ePrint Archive, arXiv:1410.5401.

[31] Graves , A., Wayne , G., Reynolds , M., , 2016. Hybrid computing using a neural network with dynamic external memory.Nature, 538(7626):471–476.

[32] Griffiths , T.L., Chater , N., Kemp , C., , 2010. Probabilistic models of cognition: exploring representations and inductive biases.Trends Cogn. Sci., 14(8):357–364.

[33] Guilford , J.P., 1967. The Nature of Human Intelligence. McGraw-Hill, New York, USA.

[34] Hagan , M.T., Demuth , H.B., Beale , M.H., , 2002. Neural Network Design. PWS Publishing Co., Boston, USA.

[35] Hilovska , K., Koncz , P., 2012. Application of artificial intelligence and data mining techniques to financial markets.ACTA VSFS, 6:62–76.

[36] Hiskens , I.A., Davy , R.J., 2001. Exploring the power flow solution space boundary.IEEE Trans. Power Syst., 16(3):389–395.

[37] Hoffman , R., 1998. Integer Programming Models for Ground-Holding in Air Traffic Flow Management. PhD Thesis, University of Maryland, College Park, USA.

[38] Holland , J.H., 1992. Adaptation in Natural and Artificial Systems: an Introductory Analysis with Applications to Biology, Control and Artificial Intelligence. MIT Press.

[39] Honey , C.J., Thivierge , J.P., Sporns , O., 2010. Can structure predict function in the human brain?NeuroImage, 52(3):766–776.

[40] Hu , P., Zhou , S., Ding , W.Z., , 2010. The comprehensive measurement model of the member importance in social networks. Int. Conf. on Management and Service Science, p.1–4.

[41] Hu , P., Wen , C.L., Pan , D., 2013. The mutual relationship among external network, internal resource, and competitiveness of enterprises.Sci. Res. Manag., V(4):90–98 (in Chinese).

[42] Hughes , D., Camp , C., O’Hara , J., , 2016. Health resource use following robot-assisted surgery versus open and conventional laparoscopic techniques in oncology: analysis of English secondary care data for radical prostatectomy and partial nephrectomy.BJU Int., 117(6):940–947.

[43] Im , D.Y., Ryoo , Y.J., Kim , D.Y., , 2009. Unmanned driving of intelligent robotic vehicle. ISIS Proc. 10th Symp. on Advanced Intelligent Systems, p.213–216.

[44] Ioffe , A.D., 1979. Necessary and sufficient conditions for a local minimum. 3: second order conditions and augmented duality.SIAM J. Contr. Opt., 17(2):266–288.

[45] Janis , I.L., Mann , L., 1977. Decision Making: a Psychological Analysis of Conflict, Choice, and Commitment. Free Press, New York, USA.

[46] Jennings , N.R., 2000. On agent-based software engineering artificial intelligence.Artif. Intell., 117(2):277–296.

[47] Johnson , M., Bradshaw , J.M., Feltovich , P.J., , 2014. Coactive design: designing support for interdependence in joint activity. Electr. Eng. Math. Comput. Sci., 3(1):43–49.

[48] Johnson , S., Slaughter , V., Carey , S., 1998. Whose gaze will infants follow? The elicitation of gaze-following in 12-month-olds.Devel. Sci., 1(2):233–238.

[49] Jordan , M.I., 2016. On computational thinking, inferential thinking and data science. Proc. 28th ACM Symp. on Parallelism in Algorithms and Architectures, p.47.

[50] Kourtzi , Z., Kanwisher , N., 2000. Activation in human MT/MST by static images with implied motion.J. Cogn. Neurosci., 12(1):48–55.

[51] Lake , B.M., Salakhutdinov , R., Tenenbaum , J.B., 2015. Human-level concept learning through probabilistic program induction.Science, 350(6266):1332–1338.

[52] Lake , B.M., Ullman , T.D., Tenenbaum , J.B., , 2016. Building machines that learn and think like people.Behav. Brain Sci., 22:1–101.

[53] Ledford , H., 2015. How to solve the world’s biggest problems.Nature, 525:308–311.

[54] Lewis , D.D., 1998. Naive (Bayes) at forty: the independence assumption in information retrieval. European Conf. on Machine Learning, p.4–15.

[55] Lillicrap , T.P., Hunt , J.J., Pritzel , A., , 2016. Continuous control with deep reinforcement learning. ePrint Archive, arXiv:1509.02971.

[56] Lippmann , R.P., 1987. An introduction to computing with neural nets.IEEE ASSP Mag., 4(2):4–22.

[57] Liyanage , J.P., 2012. Hybrid Intelligence Through Business Socialization and Networking: Managing Complexities in the Digital Era. IGI Global, Hershey, USA.

[58] Marchiori , D., Warglien , M., 2008. Predicting human interactive learning by regret-driven neural networks.Science, 319(5866):1111–1113.

[59] Marr , D., 1977. Artificial intelligence—a personal view.Artif. Intell., 9(1):37–48.

[60] Martin , J., 2007. The Meaning of the 21st Century: a Vital Blueprint for Ensuring Our Future. Random House.

[61] McCarthy , J., Hayes , P.J., 1987. Some Philosophical Problems from the Standpoint of Artificial Intelligence. Morgan Kaufmann Publishers Inc., Burlington, USA.

[62] Michalski , R.S., Carbonell , J.G., Mitchell , T.M., 1984. Machine Learning: an Artificial Intelligence Approach. Springer Science & Business Media, Berlin, Germany.

[63] Mikolov , T., Karafiát , M., Burget , L., , 2010. Recurrent neural network based language model. Conf. of the Int. Speech Communication Association, p.1045–1048.

[64] Minsky , M., 1961. Steps toward artificial intelligence.Proc. IRE, 49(1):8–30.

[65] Mirza , M., Osindero , S., 2014. Conditional generative adversarial nets. ePrint Archive, arXiv:1411.1784.

[66] Mizumoto , M., 1982. Comparison of fuzzy reasoning methods.Fuzzy Sets Syst., 8(3):253–283.

[67] Mnih , V., Kavukcuoglu , K., Silver , D., , 2013. Playing Atari with deep reinforcement learning. ePrint Archive, arXiv:1312.5602.

[68] Mnih , V., Kavukcuoglu , K., Silver , D., , 2015. Humanlevel control through deep reinforcement learning.Nature, 518(7540):529–533.

[69] Moran , J., Desimone , R., 1985. Selective Attention Gates Visual Processing in the Extrastriate Cortex. MIT Press, Cambridge, USA.

[70] Muir , B.M., 1994. Trust in automation: part I. Theoretical issues in the study of trust and human intervention in automated systems.Ergonomics, 37(11):1905–1922.

[71] Nash , J.F., 1950. Equilibrium points in n-person games.PNAS, 36(1):48–49.

[72] Navigli , R., Ponzetto , S.P., 2012. Babelnet: the automatic construction, evaluation and application of a wide-coverage multilingual semantic network.Artif. Intell., 193(6):217–250.

[73] Newell , A., Simon , H.A., 1972. Human Problem Solving. Prentice-Hall, Englewood Cliffs, USA.

[74] Nilsson , N.J., 1965. Learning Machines: Foundations of Trainable Pattern-Classifying Systems. McGraw-Hill, New York, USA.

[75] Nissen , M.J., Bullemer , P., 1987. Attentional requirements of learning: evidence from performance measures. Cogn. Psychol., 19(1):1–32.

[76] Noh , H., Hong , S., Han , B., 2015. Learning deconvolution network for semantic segmentation. IEEE Int. Conf. on Computer Vision, p.1520–1528.

[77] Norman , K.A., O’Reilly , R.C., 2003. Modeling hippocampal and neocortical contributions to recognition memory: a complementary-learning-systems approach.Psychol. Rev., 110(4):611–646.

[78] Ogura , T., Yamada , J., Yamada , S.I., , 1989. A 20 kbit associative memory lSI for artificial intelligence machines. IEEE J. Sol.-State Circ., 24(4):1014–1020.

[79] O’Keefe , J., Nadel , L., 1978. The Hippocampus as a Cognitive Map. Clarendon Press, Oxford.

[80] O’Leary , D.E., 2013. Artificial intelligence and big data.IEEE Intell. Syst., 28(2):96–99.

[81] Pan , Y.H., 2016. Heading toward artificial intelligence 2.0.Engineering, 2(4):409–413.

[82] Park , C.C., Kim , G., 2015. Expressing an image stream with a sequence of natural sentences. Advances in Neural Information Processing Systems, p.73–81.

[83] Poole , D., Mackworth , A., Goebel , R., 1997. Computational Intelligence: a Logical Approach. Oxford University Press, Oxford, UK.

[84] Premack , D., Premack , A.J., 1997. Infants attribute value to the goal-directed actions of self-propelled objects.J. Cogn. Neurosci., 9(6):848–856.

[85] Pylyshyn , Z.W., 1984. Computation and Cognition: Toward a Foundation for Cognitive Science. The MIT Press, Cambridge, Massachusetts, USA.

[86] Rachlin , H., 2012. Making IBM’s computer, Watson, human.Behav. Anal., 35(1):1–16.

[87] Radford , A., Metz , L., Chintala , S., 2015. Unsupervised representation learning with deep convolutional generative adversarial networks. ePrint Archive, arXiv:1511.06434.

[88] Rashevsky , N., 1964. Man-machine interaction in automobile driving. Prog. Biocybern., 42:188–200.

[89] Rasmussen , C.E., 2000. The infinite Gaussian mixture model. Advances in Neural Information Processing Systems, p.554–560.

[90] Rehder , B., Hastie , R., 2001. Causal knowledge and categories: the effects of causal beliefs on categorization, induction, and similarity.J. Exp. Psychol., 130(3):323–360.

[91] Russell , S.J., Norvig , P., 1995. Artificial Intelligence: a Modern Approach. Prentice Hall, Englewood Cliffs, USA.

[92] Salimans , T., Goodfellow , I., Zaremba , W., , 2016. Improved techniques for training gans. Advances in Neural Information Processing Systems, p.2226–2234.

[93] Salvi , C., Bricolo , E., Kounios , J., , 2016. Insight solutions are correct more often than analytic solutions.Think. Reason., 22(4):443–460.

[94] Samuel , A.L., 1988. Some studies in machine learning using the game of checkers.IBM J. Res. Dev., 44(1-2):206–226.

[95] Saripalli , S., Montgomery , J.F., Sukhatme , G., 2003. Visually guided landing of an unmanned aerial vehicle.IEEE Trans. Robot. Autom., 19(3):371–380.

[96] Saxe , R., Carey , S., 2006. The perception of causality in infancy.ACTA Psychol., 123(1-2):144–165.

[97] Schlottmann , A., Ray , E.D., Mitchell , A., , 2006. Perceived physical and social causality in animated motions: spontaneous reports and ratings.ACTA Psychol., 123(1-2):112–143.

[98] Schwartz , T., Zinnikus , I., Krieger , H.U., , 2016. Hybrid teams: flexible collaboration between humans, robots and virtual agents. German Conf. on Multiagent System Technologies, p.131–146.

[99] Selfridge , O.G., 1988. Pandemonium: a paradigm for learning. National Physical Laboratory Conf., p.511–531.

[100] Shader , R.I., 2016. Some reflections on IBM Watson and on women’s health.Clin. Therap., 38(1):1–2.

[101] Sharp , C.S., Shakernia , O., Sastry , S.S., 2001. A vision system for landing an unmanned aerial vehicle. IEEE Int. Conf. on Robotics & Automation, p.1720–1727.

[102] Shrivastava , P., 1995. Ecocentric management for a risk society.Acad. Manag. Rev., 20(1):118–137.

[103] Shuaibu , B.M., Norwawi , N.M., Selamat , M.H., , 2015. Systematic review of Web application security development model.Artif. Intell. Rev., 43(2):259–276.

[104] Silver , D., Huang , A., Maddison , C.J., , 2016. Mastering the game of Go with deep neural networks and tree search.Nature, 529(7587):484–489.

[105] Simon , H.A., 1969. The Sciences of the Artificial. MIT Press, Cambridge, USA.

[106] Son , D., Lee , J., Qiao , S., , 2014. Multifunctional wearable devices for diagnosis and therapy of movement disorders.Nat. Nanotechnol., 9(5):397–404.

[107] Sternberg , R.J., 1984. Beyond IQ: a triarchic theory of human intelligence. Br. J. Educat. Stud., 7(2):269–287.

[108] Sternberg , R.J., Davidson , J.E., 1983. Insight in the gifted.Educat. Psychol., 18(1):51–57.

[109] Stone , P., Brooks , R., Brynjolfsson , E., , 2016. Artificial Intelligence and Life in 2030. One Hundred Year Study on Artificial Intelligence: Report of the 2015-2016 Study Panel, Stanford University, Stanford, USA.

[110] Sun , Y., Wang , X.G., Tang , X.O., 2014. Deep learning face representation from predicting 10,000 classes. IEEE Conf. on Computer Vision and Pattern Recognition, p.1891–1898.

[111] Szegedy , C., Zaremba , W., Sutskever , I., , 2013. Intriguing properties of neural networks. ePrint Archive, arXiv:1312.6199.

[112] Szolovits , P., Patil , R.S., Schwartz , W.B., 1988. Artificial intelligence in medical diagnosis.Ann. Int. Med., 108(1):80–87.

[113] Tenenbaum , J.B., Kemp , C., Griffiths , T.L., , 2011. How to grow a mind: statistics, structure, and abstraction. Science, 331(6022):1279–1285.

[114] Thielscher , M., 1997. Ramification and causality.Artif. Intell., 89(1-2):317–364.

[115] Thielscher , M., 2001. The qualification problem: a solution to the problem of anomalous models.Artif. Intell., 131(1-2):1–37.

[116] Thrun , S., Burgard , W., Fox , D., 1998. A probabilistic approach to concurrent mapping and localization for mobile robots.Mach. Learn., 5(3):253–271.

[117] Tolman , E.C., 1948. Cognitive maps in rats and men.Psychol. Rev., 55(4):189–208.

[118] Tremoulet , P.D., Feldman , J., 2000. Perception of animacy from the motion of a single object.Perception, 29(8):943–951.

[119] Tversky , A., Kahneman , D., 1983. Extensional versus intuitive reasoning: the conjunction fallacy in probability judgment.Psychol. Rev., 90(4):293–315.

[120] van den Oord , A., Kalchbrenner , N., Kavukcuoglu , K., 2016. Pixel recurrent neural networks. ePrint Archive, arXiv:1601.06759.

[121] Varaiya , P., 1993. Smart car on smart roads: problems of control.IEEE Trans. Autom. Contr., 38(2):195–207.

[122] Waldrop , M.M., 2015. Autonomous vehicles: no drivers required.Nature, 518(7537):20–23.

[123] Walters , M.L., Koay , K.L., Syrdal , D.S., , 2013. Companion robots for elderly people: using theatre to investigate potential users’ views. IEEE Ro-Man, p.691–696.

[124] Wang , F.Y., 2004. Artificial societies, computational experiments, and parallel systems: a discussion on computational theory of complex social-economic systems.Compl. Syst. Compl. Sci., 1(4):25–35.

[125] Wang , F.Y., Wang , X., Li , L.X., , 2016. Steps toward parallel intelligence.IEEE/CAA J. Autom. Sin., 3(4):345–348.

[126] Wang , J.J., Ma , Y.Q., Chen , S.T., , 2017. Fragmentation knowledge processing and networked artificial.Seieat. Sin. Inform., 47(1):1–22.

[127] Wang , L.M., Xiong , Y.J., Wang , Z., , 2016. Temporal segment networks: towards good practices for deep action recognition.LNCS, 9912:20–36.

[128] Wei , P., Zheng , N.N., Zhao , Y.B., , 2013. Concurrent action detection with structural prediction. IEEE Int. Conf. on Computer Vision, p.3136–3143.

[129] Wei , P., Zhao , Y., Zheng , N., , 2016. Modeling 4D human-object interactions for joint event segmentation, recognition, and object localization.IEEE Trans. Softw. Eng.

[130] Williams , R.J., Zipser , D., 1989. A learning algorithm for continually running fully recurrent neural networks.Neur. Comput., 1(2):270–280.

[131] Williams , W.M., Sternberg , R.J., 1988. Group intelligence: why some groups are better than others.Intelligence, 12(4):351–377.

[132] Xiao , C.Y., Dymetman , M., Gardent , C., 2016. Sequencebased structured prediction for semantic parsing. Meeting of the Association for Computational Linguistics, p.1341–1350.

[133] Yau , S.S., Gupta , S.K.S., Karim , F., , 2003. Smart classroom: enhancing collaborative learning using pervasive computing technology. ASEE Annual Conf. and Exposition, p.13633–13642.

[134] Yegnanarayana , B., 1994. Artificial neural networks for pattern recognition.Sadhana, 19(2):189–238.

[135] Youseff , L., Butrico , M., da Silva , D., 2008. Toward a unified ontology of cloud computing. Grid Computing Environments Workshop, p.1–10.

[136] Zadeh , L.A., 1996. Fuzzy logic and approximate reasoning.In: Advances in Fuzzy Systems- Applications and Theory: Volume 6. Fuzzy Sets, Fuzzy Logic, and Fuzzy Systems. World Scientific Publishing, Singapore, p.238–259.

[137] Zhao , Y.Y., Qin , B., Liu , T., 2010. Sentiment analysis.J. Softw., 21(8):1834–1848.

[138] Zheng , N.N., Tang , S.M., Cheng , H., , 2004. Toward intelligent driver-assistance and safety warning systems.IEEE Intell. Syst., 19(2):8–11.

RIGHTS & PERMISSIONS

Zhejiang University and Springer-Verlag Berlin Heidelberg