Conclusions and Future Directions

  • Ali Mohammad SaghiriEmail author
  • M. Daliri Khomami
  • Mohammad Reza Meybodi
Part of the SpringerBriefs in Applied Sciences and Technology book series (BRIEFSAPPLSCIENCES)


In this book, we presented a comprehensive analysis of the principal tasks related to the intelligent models of random walk based on learning automata. After introducing the random walk, we focused on its main drawbacks and weak performance in real-world applications. Then, three intelligent models were established on the bases of random walk. Moreover, theoretical analysis and convergence behavior of the proposed models based on weak convergence theory and Ordinary Differential Equation (ODE) were studied. In addition, the proposed models were applied in two large-scale complex networks such as peer-to-peer networks and social networks. It should be noted that this book presents a new horizon for future research based on random walk and learning systems. The rationale behind the proposed models can be extended with other learning techniques such as Q-learning. In the other hand, there are numerous versions of random walk which should be reconfigured with learning methods in real-world applications. In this chapter, the conclusions and the future directions are explained in more detail.


Intelligent models of random walk Learning systems Q-Learning 


  1. 1.
    Walter W (1998) Ordinary differential equations. SpringerGoogle Scholar
  2. 2.
    Narendra KS, Thathachar MAL (1989) Learning automata: an introduction. Prentice HallGoogle Scholar
  3. 3.
    Khomami MMD, Rezvanian AR, Meybodi MR (2016) Distributed learning automata-based algorithm for community detection in complex networks. Int J Mod Phys B 30:1650042MathSciNetCrossRefGoogle Scholar
  4. 4.
    Beigy H, Meybodi MR (2004) A mathematical framework for cellular learning automata. Adv Complex Syst 3:295–319MathSciNetCrossRefGoogle Scholar
  5. 5.
    Rezvanian A, Saghiri AM, Vahidipour M, Esnaashari M, Meybodi MR (2018) Recent advances in learning automata. SpringerGoogle Scholar
  6. 6.
    Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. Cambridge University PressGoogle Scholar
  7. 7.
    Ma T, Xia Z, Yang F (2017) An ant colony random walk algorithm for overlapping community detection. International conference on intelligent data engineering and automated learning. Springer, China, pp 20–26Google Scholar
  8. 8.
    Haykin S (1994) Neural networks: a comprehensive foundation. Prentice Hall PTRGoogle Scholar
  9. 9.
    Osborne MJ, Rubinstein A (1994) A course in game theory. MIT pressGoogle Scholar
  10. 10.
    Wang F, Camacho E, Xu K (2009) Positive influence dominating set in online social networks. In: Du D-Z, Hu X, Pardalos PM (eds) Combinatorial optimization and applications. Springer, Berlin Heidelberg, pp 313–321CrossRefGoogle Scholar
  11. 11.
    Rezvanian A, Meybodi MR (2016) Stochastic graph as a model for social networks. Comput Hum Behav 64:621–640CrossRefGoogle Scholar
  12. 12.
    Rezvanian AR, Meybodi MR (2015) A new learning automata based sampling algorithm for social networks. Int J Commun Syst. Scholar
  13. 13.
    Rezvanian A, Meybodi MR (2017) A new learning automata-based sampling algorithm for social networks. Int J Commun Syst 30:e3091CrossRefGoogle Scholar

Copyright information

© The Author(s), under exclusive license to Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Ali Mohammad Saghiri
    • 1
    Email author
  • M. Daliri Khomami
    • 1
  • Mohammad Reza Meybodi
    • 1
  1. 1.Amirkabir University of TechnologyTehranIran

Personalised recommendations