Artificial Intelligence Design, from Research to Practice

  • Wanyu HeEmail author
  • Xiaodi Yang
Conference paper


As artificial intelligence (AI) technologies continually evolve, they penetrate multiple industries and extend a variety of applications such as image discrimination, voice assistant and smart translator etc. Inspired by the trend of AI, this paper reflected on the traditional design approaches in urban and architecture field, and tried to address the essential problems in the existing ways by combining pioneer design approaches (associative design, algorithmic design) and machine learning, deep learning methods. Taking the feasibility and limitations of the associative design and algorithmic design into account, an artificial intelligence design approach was explored and demonstrated with corresponding practical cases. Based on outcomes of research and practice, this paper further discussed the possibility and application scenarios of AI design in the future.


Artificial intelligence design Algorithmic design Associative design Machine learning Deep learning 


  1. 1.
    Koolhaas, R., Gianotten, D.: MTALKS. In: Rem Koolhaas and David Gianotten on countryside. (2017). Accessed 10 Mar 2019
  2. 2.
    Li, N., Mao, M.: Probing into the relationship between function and form in architectural design. Urban Constr. Theory Res. (14) (2014)Google Scholar
  3. 3.
    Chaslin, F.: Koolhaas Talks About Koolhaas: Two Conversations and Other. Lin, Y.X. translated. Garden city culture enterprise co. LTD, Taipei (2003)Google Scholar
  4. 4.
    Foucault, M.: Security, Territory and Population: French Academy Speech Series, 1977–1978. Qian, H., Chen, X. translated. Shanghai People’s Publishing House, Shanghai (2010)Google Scholar
  5. 5.
    Tummer, P.: Associative Design1–6. Berlage Institute (2004–2010)Google Scholar
  6. 6.
    Gatys, L.A., Ecker, A.S., Bethge, M.: A neural algorithm of artistic style. Comput. Sci. (2015).
  7. 7.
    Krizhevsky, A., Sutskever, I., Hinton, G.: Imagenet classification with deep convolutional neural networks. Adv. Neural. Inf. Process. Syst. 1, 1097–1105 (2012)Google Scholar
  8. 8.
    He, W.Y.: Rethink parametric design-its theory, research, summarization and practice. City Archit. 2012(10), 62–67 (2012)Google Scholar
  9. 9.
    Silver, D., Huang, A., Maddison, C.J., et al.: Mastering the game of go with deep neural networks and tree search. Nature 529, 484–489 (2016)CrossRefGoogle Scholar
  10. 10.
    Goodfellow, I.J., Abadie, J., Mirza, M., et al.: Generative adversarial nets. In: Montreal: Advances in Neural Information Processing Systems, pp. 2672–2680 (2014)Google Scholar
  11. 11.
    Liu, Q., Li, Y., Duan, H., et al.: A survey of knowledge mapping construction techniques. Comput. Res. Dev. 3, 582–600 (2016)Google Scholar
  12. 12.
    Silver, D., Schrittwieser, J., et al.: Mastering the game of go without human knowledge. Nature 550, 354–359 (2017)CrossRefGoogle Scholar
  13. 13.
    LeCun, Y., Bengio, Y., Hinton, G.L.: Deep learning. Nature 14539 (2015)Google Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  1. 1.Xkool Tech. Co. LDT.Nanshan, ShenzhenChina

Personalised recommendations