期刊首页 优先出版 当期阅读 过刊浏览 作者中心 关于期刊 English

《工程(英文)》 >> 2019年 第5卷 第5期 doi: 10.1016/j.eng.2019.08.005

介尺度中的复杂性——人工智能发展中的共性挑战

a State Key Laboratory of Multiphase Complex Systems, Institute of Process Engineering, Chinese Academy of Sciences, Beijing
100190, China
b School of Chemical Engineering, University of Chinese Academy of Sciences, Beijing 100049, China
c School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China

收稿日期: 2019-07-15 修回日期: 2019-07-29 录用日期: 2019-08-12 发布日期: 2019-08-21

下一篇 上一篇

摘要

探索复杂系统背后的物理机制并加以有效利用,是处理各类复杂事物的普适性方法。大数据的兴起与计算能力的提升,加之优化算法的改进,触发了以深度学习为驱动的人工智能变革,并在多个应用领域取得了突破性进展。然而,深度学习难以揭示所解决问题的底层逻辑和物理内涵,进而阻碍了其进一步发展。介科学提出了理解复杂系统时空多尺度结构的原理和方法,已在多个领域见到成效。本文提出“基于介科学的人工智能”研究范式,将介科学原理和方法应用于深度学习模型设计,旨在弥补其模型脱离问题物理原型这一根本性问题,探索人工智能可持续发展的有效途径。

图片

图1

图2

图3

参考文献

[ 1 ] The State Council of China. Development Plans of New Generation Artificial Intelligence; 2017.

[ 2 ] European Commission. Artificial Intelligence for Europe; 2018.

[ 3 ] UK Government Office for Science. Artificial intelligence: opportunities and implications for the future of decision making; 2016.

[ 4 ] National Science and Technology Council, Networking and Information Technology Research and Development Subcommittee. The National Artificial Intelligence Research and Development Strategic Plan. Washington: Executive Office of the President of the United State; 2016 Oct.

[ 5 ] Chang CL, Lee RC. Symbolic logic and mechanical theorem proving. New York: Academic Press; 1973. 链接1

[ 6 ] Puppe F. Systematic introduction to expert systems. Berlin: Springer-Verlag; 1993. 链接1

[ 7 ] Jordan MI, Mitchell TM. Machin learning: trends, perspectives, and prospects. Science 2015;349(6245):255–60. 链接1

[ 8 ] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Proceedings of the Neural Information Processing Systems; 2012 Dec 3–8; Lake Tahoe, NV, USA. San Diego: Neural Information Processing Systems Foundation; 2012. 链接1

[ 9 ] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR); 2015 May 7–9; San Diego, CA, USA; 2015. arXiv: 1409.1556. 链接1

[10] He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the 28th IEEE Conference on Computer Vision and Pattern Recognition; 2015 June 8–10; Boston, MA, USA. New York: IEEE; 2016. 链接1

[11] Hinton G, Deng L, Yu D, Dahl G, Mohamed A, Jaitly N, et al. Deep neural networks for acoustic modeling in speech recognition. IEEE Signal Process Mag 2012;29:82–97. 链接1

[12] Sainath TN, Mohamed A, Kingsbury B, Ramabhadran B. Deep convolutional neural networks for LVCSR. In: Proceedings of the 38th IEEE International Conference on Acoustics, Speech and Signal Processing; 2013 May 26–31; Vancouver, Canada. New York: IEEE; 2013. 链接1

[13] Ma J, Sheridan RP, Liaw A, Dahl GE, Svetnik V. Deep neural nets as a method for quantitative structure-activity relationships. J Chem Inf Model 2015;55:263–74. 链接1

[14] Ciodaro T, Deva D, De Seixas JM, Damazio D. Online particle detection with neural networks based on topological calorimetry information. J Phys Conf Ser 2012;368:12–30. 链接1

[15] Helmstaedter M, Briggman KL, Turaga SC, Jain V, Seung S, Denk W. Connectomic reconstruction of the inner plexiform layer in the mouse retina. Nature 2013;500:168–74. 链接1

[16] Shallue V, Vanderburg A. Identifying exoplanets with deep learning: a fiveplanet resonant chain around Kepler-80 and an eighth planet around Kepler- 90. Astron J 2018;155:94–115. 链接1

[17] Esteva A, Kuprel B, Novova RA, Ko J, Swetter SM, Blau HM, et al. Dermatologistlevel classification of skin cancer with deep neural networks. Nature 2017;552:23–5. 链接1

[18] Leung MK, Xiong HY, Lee LJ, Frey BJ. Deep learning of the tissue-regulated splicing code. Bioinformatics 2014;30:121–9. 链接1

[19] Xiong H, Alipanahi B, Lee LJ, Bretschneider H, Merico D, Yuen RKC, et al. The human splicing code reveals new insights into the genetic determinants of disease. Science 2015;347(6218):1254806. 链接1

[20] LeCun Y, Bengio Y, Hinton G. Deep learning. Nature 2015;521:436–44. 链接1

[21] Rumelhart DE, Hinton GE, Williams RJ. Learning representations by backpropagating errors. Nature 1986;323(6088):533–6. 链接1

[22] Vapnik V. The nature of statistical learning theory. New York: Springer; 1998. 链接1

[23] Elsken T, Metzen JH, Hutter F. Neural architecture search: a survey. J Mach Learn Res 2019;20:1–21. 链接1

[24] Mendoza H, Klein A, Feurer M, Springenberg JT, Hutter F. Towards automatically-tuned neural networks. In: Proceedings of the International Conference on Machine Learning; 2016 Jun 19–24; New York, NY, USA. JMLR Workshop Proc 2016;64:58–65. 链接1

[25] Zoph B, Le QV. Neural architecture search with reinforcement learning. In: Proceedings of the 5rd International Conference on Learning Representations; 2017 April 24–26; Toulon, France. La Jolla: ICLR; 2017. 链接1

[26] Real E, Aggarwal A, Huang Y, Le QV. Aging evolution for image classifier architecture search. In: Proceedings of the 23th AAAI Conference on Artificial Intelligence; 2019 Jan 27–Feb 1; Honolulu, HI, USA. Palo Alto: AAAI; 2019. 链接1

[27] Zeiler M, Fergus R. Visualizing and understanding convolutional networks. In: Proceedings of the 13th European Conference on Computer Vision; 2014 Sep 6–12; Zurich, Switzerland. Cham: Springer; 2014. 链接1

[28] Li J, Ge W, Yang N, Liu X, Wang L, He X, et al. From multiscale modeling to meso-science. Berlin: Springer; 2013. 链接1

[29] Li J, Tung Y, Kwauk M. Method of energy minimization in multi-scale modeling of particle-fluid two-phase flow. In: Proceedings of the 2nd International Conference on Circulating Fluidized Beds; 1988 Mar 14–18; Compiégne, France. Circ Fluid Bed Technol; 1988:89–103. 链接1

[30] Yang N, Wu Z, Chen J, Wang Y, Li J. Multi-scale analysis of gas–liquid interaction and CFD simulation of gas–liquid flow in bubble columns. Chem Eng Sci 2011;66(14):3212–22. 链接1

[31] Wang L, Qiu X, Zhang L, Li J. Turbulence originating from the compromise-incompetition between viscosity and inertia. Chem Eng J 2016;300:83–97. 链接1

[32] Li J, Zhang Z, Ge W, Sun Q, Yuan J. A simple variational criterion for turbulent flow in pipe. Chem Eng Sci 1999;54(8):1151–4. 链接1

[33] Ren Y, Gao J, Xu J, Ge W, Li J. Key factors in chaperonin-assisted protein folding. Particuology 2012;10(1):105–16. 链接1

[34] Huang WL, Li J. Mesoscale model for heterogeneous catalysis based on the principle of compromise in competition. Chem Eng Sci 2016;147:83–90. 链接1

[35] Li J, Huang W, Chen J, Ge W, Hou C. Mesoscience based on the EMMS principle of compromise in competition. Chem Eng J 2018;333:327–35. 链接1

[36] Li J, Huang W. From multiscale to mesoscience: addressing mesoscales in mesoregimes of different levels. Annu Rev Chem Biomol Eng 2018;9:41–60. 链接1

[37] Kandel ER, Schwartz JH, Jessell TM, Siegelbaum SA, Hudspeth AJ, Mack S. Principles of neural science. 5th ed. New York: McGraw-Hill Education; 2012. 链接1

[38] Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van den Driessche G, et al. Mastering the game of Go with deep neural networks and tree search. Nature 2016;529(7587):484–9. 链接1

[39] Silver D, Huang A, Maddison CJ, Guez A, Sifre L, Van den Driessche G, et al. Mastering the game of Go without human knowledge. Nature 2016;550:484–9. 链接1

[40] Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. In: Proceedings of the Advances in Neural Information Processing Systems; 2014 Dec 8–13; Montréal, Canada. San Diego: Neural Information Processing Systems Foundation; 2014. 链接1

相关研究