Cellular Neural Networks

  • Xuewei Li
  • Jinpei Wu
  • Xueyan Li


As stated in the chapter of Cellular Genetic Algorithm, an individual cell plays the roles of both “chromosome” and “gene”. Though the roles are different, they all reflect the function of “information transmission by the rules” and the intelligent form of the cells. To continue thinking along this path, may the cellular automata continue to play the role of some elements in other intelligent algorithms so as to realize some complex operations of the intelligent algorithm by using “computing by the rules” of the cells? If the answer is “yes”, then what are the characteristics of such a smart algorithm? Where is the linking point? What will be the effect? If not, where are the difficulties? Will this be able to provide some ideas for the improvement of the intelligent algorithm?


  1. Acedo, L. (2009). A cellular automaton model for collective neural dynamics. Mathematical and Computer Modelling, 50(5–6), 717–725.CrossRefGoogle Scholar
  2. Bandman, O. (2002). Cellular–neural automaton: A hybrid model for reaction-diffusion simulation. Future Generation Computer Systems, 18(6), 737–745.CrossRefGoogle Scholar
  3. Cattaneo, G., & Vogliotti, C. Q. (1997). The, “magic” rule spaces of neural-like elementary cellular automata. Theoretical Computer Science, 178(1), 77–102.CrossRefGoogle Scholar
  4. Dohler, F., Mormanna, F., Weber, B., et al. (2008). A cellular neural network based method for classification of magnetic resonance images: Towards an automated detection of hippocampal sclerosis. Journal of Neuroscience Methods, 170(2), 324–331.CrossRefGoogle Scholar
  5. He, X., & Liang, J. (2000). Several theoretical issues on the process neuron networks. China Engineering Science, 2(12), 40–44.Google Scholar
  6. He, X., Liang, J., & Xu, S. (2001). The training and applications of the process neuron networks. China Engineering Science, 3(4), 31–35.Google Scholar
  7. Kim, K.-J., & Cho, S.-B. (2006). Evolved neural networks based on cellular automata for sensory-motor controller. Neurocomputing, 69(16–18), 2193–2207.CrossRefGoogle Scholar
  8. Li, L., & Mai, X. (2009). Dynamic simulation and prediction of karst rocky desertification based on CA—ANN spatial-temporal pattern. Journal of Guangxi Normal University: Natural Science Edition, 26(1), 84–89.Google Scholar
  9. Li, X., Sun, Y., & Wu, J. (2011). A new kind of cellular network model. Journal of Wuyi University: Natural Science Edition, 25(4), 14–21.Google Scholar
  10. Li, X., & Ye, J. (2005). Neural network based cellular automata and their applications on complex land utilization system simulations. Geography Research, 24(1), 19–27.Google Scholar
  11. Liu, L., Li, P., Li, X., et al. (2011). The applications of discrete process neural network in time series prediction. Computer Engineering and Applications, 47(32), 224–227.Google Scholar
  12. Tzionas, P. G. (2001). A cellular neural network modelling the behavior of reconfigurable cellular automata. Microprocessors and Microsystems, 25(8), 379–387.CrossRefGoogle Scholar
  13. Xu, S., He, X., & Wang, B. (2007). A study on time variation based input-output process neuron network and its learning algorithm. Control and Decision, 22(12), 1425–1428.Google Scholar
  14. Yang, G., Cui, P., & Li, L. (2001). The applications and realizations of genetic algorithm in neural network control. Journal of System Simulations, 13(5), 567–570.Google Scholar
  15. Zhao, J., Chen, H., & Huiping, X. (2007). Cellular automaton and neural network combined simulations on land evolution. Journal of Tongji University: Natural Science Edition, 35(8), 1128–1132.Google Scholar

Copyright information

© Beijing Jiaotong University Press and Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  1. 1.Beijing Union UniversityBeijingChina
  2. 2.Wuyi UniversityJiangmenChina
  3. 3.Beijing Jiaotong universityBeijingChina

Personalised recommendations