Skip to main content
SpringerLink
Log in

MEAHO: Membrane Evolutionary Algorithm for Hyperparameter Optimization of Deep Convolutional Neural Networks

  • Conference paper
  • First Online:
Computer Applications (CCF NCCA 2023)

Part of the book series: Communications in Computer and Information Science ((CCIS,volume 1959))

Included in the following conference series:

  • 106 Accesses

Abstract

Membrane algorithm has been used to solve many optimization problems since it was put forward. These methods used the membrane algorithm as a container for other algorithms to solve many problems, such as, traveling salesman problem, the knapsack problem and so on. In this paper, from the angle of membrane algorithm, the solution of hyperparameter optimization problem by membrane algorithm is explored, with the hyperparameter space divided by lattice method, which transformed into membrane structure subsequently. For the evolution of membrane, the entropy reduction principle is proposed. Compared with other membrane algorithms, this paper solves the optimization problem from the membrane algorithm itself, designs the corresponding algorithm for the membrane structure, and obtains the experimental results through CNN experiment.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 59.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 79.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

References

  1. Păun, G.: Computing with membranes. J. Comput. Syst. Sci. 61(1), 108–143 (2000)

    Article  MathSciNet  MATH  Google Scholar 

  2. Martín-Vide, C., Păun, G., Pazos, J., Rodríguez-Patón, A.: Tissue P systems. Theor. Comput. Sci. 296(2), 295–326 (2003)

    Article  MathSciNet  MATH  Google Scholar 

  3. Alsalibi, B. et al. A comprehensive survey on the recent variants and applications of membrane-inspired evolutionary algorithms. Archives of Computational Methods in Engineering: 1–17 (2022) https://doi.org/10.1007/s11831-021-09693-5

  4. Pan, L., Wu, T., Su, Y., Vasilakos, A.V.: Cell-like spikingneural P systems with request rules. IEEE Trans. Nanobiosci. 16(6), 513–522 (2017)

    Article  Google Scholar 

  5. Peng, H., et al.: Spiking neural P systems with multiple channels. Neural Netw. 95, 66–71 (2017)

    Article  MATH  Google Scholar 

  6. Young, G O. Synthetic structure of industrial plastics, in Plastics, 2nd ed., vol. 3, J. Peters, Ed. New York, NY, USA: McGraw-Hill, pp. 15–64. (1964)

    Google Scholar 

  7. Chen, W K. Linear Networks and Systems. Belmont, CA, USA:Wadsworth, pp. 123–135 (1993)

    Google Scholar 

  8. Bergstra, J., et al. Algorithms for hyper-parameter optimization .In: 25th Annual Conference on Neural Information Processing Systems (NIPS 2011), vol. 24. Neural Information Processing Systems Foundation (2011)

    Google Scholar 

  9. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. nature 521(7553), 436–444 (2015)

    Google Scholar 

  10. Kennedy, J., Eberhart, R. Particle swarm optimization. In: Proceedings of ICNN’95-International Conference on Neural Networks. Vol. 4. IEEE. (1995)

    Google Scholar 

  11. Whitley, D.: A genetic algorithm tutorial. Stat. Comput. 4(2), 65–85 (1994)

    Article  Google Scholar 

  12. Bergstra, J., Bengio, Y. Random search for hyper-parameter optimization. J. Mach. Learn. Res. 13.2 (2012)

    Google Scholar 

  13. David, Omid E., Greental, I. Genetic algorithms for evolving deep neural networks. In: Proceedings of the Companion Publication of the 2014 Annual Conference on Genetic and Evolutionary Computation. (2014)

    Google Scholar 

  14. Hutter, F., Hoos, H H., Leyton-Brown, K. Sequential model-based optimization for general algorithm configuration. In: International Conference on Learning And Intelligent Optimization. Springer, Berlin, Heidelberg. (2011)

    Google Scholar 

  15. Juanjuan, H.E., Jianhua, X.I.A.O., Zehui, S.H.A.O.: An adaptive membrane algorithm for solving combinatorial optimization problems. Acta Math. Sci. 34(5), 1377–1394 (2014)

    Article  MathSciNet  MATH  Google Scholar 

  16. Lorenzo, P R., et al. Particle swarm optimization for hyper-parameter selection in deep neural networks. In: Proceedings of The Genetic and Evolutionary Computation Conference. (2017)

    Google Scholar 

  17. Montavon, G., Orr, G.B., Müller, K.-R. (eds.): Neural Networks: Tricks of the Trade: Second Edition. Springer Berlin Heidelberg, Berlin, Heidelberg (2012). https://doi.org/10.1007/978-3-642-35289-8

    Book  Google Scholar 

  18. Nishida, Taishin Y. Membrane algorithms. International Workshop on Membrane Computing. Springer, Berlin, Heidelberg. (2005). https://doi.org/10.1007/11603047_4

  19. Shahriari, B., Swersky, K., Wang, Z., Adams, R.P., de Freitas, N.: Taking the human out of the loop: a review of bayesian optimization. Proc. IEEE 104(1), 148–175 (2016). https://doi.org/10.1109/JPROC.2015.2494218

    Article  Google Scholar 

  20. Xiao, J., Huang, Y., Cheng, Z., He, J., Niu, Y.: A hybrid membrane evolutionary algorithm for solving constrained optimization problems. Optik 125(2), 897–902 (2014). https://doi.org/10.1016/j.ijleo.2013.08.032

    Article  Google Scholar 

  21. Zhang, G.-X., Gheorghe, M., Chao-Zhong, W.: A quantum-inspired evolutionary algorithm based on P systems for knapsack problem. Fund. Inform. 87(1), 93–116 (2008)

    MathSciNet  MATH  Google Scholar 

  22. Zhang, G., et al. A Novel Membrane Algorithm Based on Particle Swarm Optimization for Solving Broadcasting Problems. J. UCS 18.13: 1821–1841. (2012)

    Google Scholar 

  23. Zhang, G., Cheng, J., Gheorghe, M., Meng, Q.: A hybrid approach based on differential evolution and tissue membrane systems for solving constrained manufacturing parameter optimization problems. Appl. Soft Comput. 13(3), 1528–1542 (2013). https://doi.org/10.1016/j.asoc.2012.05.032

    Article  Google Scholar 

  24. Zhang, Gexiang, et al. A population-membrane-systeminspired evolutionary algorithm for distribution network reconfiguration. Chinese J. Electron. 23.3: 437–441. (2014)

    Google Scholar 

  25. Pan, L., Martin-Vide, C.: Solving multidimensional 0–1 knapsack problem by P systems with input and active membranes. J. Parallel and Distrib. Comput. 65(12), 1578–1584 (2005)

    Article  MATH  Google Scholar 

  26. Pérez-Jiménez, Mario J., and Agustin Riscos-Núnez. A lineartime solution to the knapsack problem using P systems with active membranes. In: International workshop on membrane computing. Springer, Berlin, Heidelberg. (2003)

    Google Scholar 

  27. Attacking NP-complete problems: Liu, Xiangrong, et al. The power of time-free tissue P systems. Neurocomputing 159, 151–156 (2015)

    Article  Google Scholar 

  28. Guo, P., Quan, C., Chen, H.: MEAMVC: A membrane evolutionary algorithm for solving minimum vertex cover problem. IEEE Access 7, 60774–60784 (2019)

    Article  Google Scholar 

  29. Golpira, H., Bevrani, H.: Application of GA optimization for automatic generation control design in an interconnected power system. Energy Convers. Manage. 52(5), 2247–2255 (2011)

    Article  Google Scholar 

  30. Delgarm, N., et al.: Multi-objective optimization of the building energy performance: a simulation-based approach by means of particle swarm optimization (PSO). Appl. Energy 170, 293–303 (2016)

    Article  Google Scholar 

  31. Zhu, H., Wang, Yi., Wang, K., Chen, Y.: Particle swarm optimization (PSO) for the constrained portfolio optimization problem. Expert Syst. Appl. 38(8), 10161–10169 (2011). https://doi.org/10.1016/j.eswa.2011.02.075

    Article  Google Scholar 

  32. Leporati, Alberto, and Pagani, D. A membrane algorithm for the min storage problem. In: International Workshop on Membrane Computing. Springer, Berlin, Heidelberg. (2006)

    Google Scholar 

  33. Bischl, B., Binder, M., Lang, M., et al.: Hyperparameter optimization: Foundations, algorithms, best practices, and open challenges. Wiley Interdisc. Rev.: Data Min. Knowl. Discovery 13(2), e1484 (2023)

    Google Scholar 

  34. Pelikan, Martin, David E. Goldberg, Erick Cantú-Paz. BOA: The bayesian optimization algorithm. In: Proceedings of The Genetic and Evolutionary Computation Conference GECCO-99. Vol. 1. (1999)

    Google Scholar 

  35. Davies, P.C.W., Rieper, E., Tuszynski, J.A.: Self-organization and entropy reduction in a living cell. Biosystems 111(1), 1–10 (2013). https://doi.org/10.1016/j.biosystems.2012.10.005

    Article  Google Scholar 

  36. G. Päun, Computing with membranes: attacking NP-complete problems, in Unconventional Models Computer. London, U.K.: Springer, pp. 94–115. (2001)

    Google Scholar 

  37. Guo, P., Hou, M., Ye, L.: MEATSP: a membrane evolutionary algorithm for solving TSP. IEEE Access 8, 199081–199096 (2020). https://doi.org/10.1109/ACCESS.2020.3035058

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Big Data and Software Engineering, Chongqing University, Chongqing, 400044, China

    Jie Mu, Jiaxin Hou & Ying Wan

Authors
  1. Jie Mu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jiaxin Hou
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ying Wan
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ying Wan .

Editor information

Editors and Affiliations

  1. Suzhou University, Suzhou, China

    Min Zhang

  2. Tsinghua University, Beijing, China

    Bin Xu

  3. Suzhou University of Science and Technology, Suzhou, China

    Fuyuan Hu

  4. Institute of Information Engineering, CAS, Beijing, China

    Junyu Lin

  5. Harbin University of Science and Technology, Harbin, China

    Xianhua Song

  6. National Academy of Guo Ding Institute of Data Science, Beijing, China

    Zeguang Lu

Rights and permissions

Reprints and permissions

Copyright information

© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Mu, J., Hou, J., Wan, Y. (2024). MEAHO: Membrane Evolutionary Algorithm for Hyperparameter Optimization of Deep Convolutional Neural Networks. In: Zhang, M., Xu, B., Hu, F., Lin, J., Song, X., Lu, Z. (eds) Computer Applications. CCF NCCA 2023. Communications in Computer and Information Science, vol 1959. Springer, Singapore. https://doi.org/10.1007/978-981-99-8764-1_20

Download citation

  • DOI: https://doi.org/10.1007/978-981-99-8764-1_20

  • Published:

  • Publisher Name: Springer, Singapore

  • Print ISBN: 978-981-99-8763-4

  • Online ISBN: 978-981-99-8764-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation