SpringerLink
Log in

Adapting modularity during learning in cooperative co-evolutionary recurrent neural networks

  • Original Paper
  • Published:
Soft Computing Aims and scope Submit manuscript

Abstract

Adaptation during evolution has been an important focus of research in training neural networks. Cooperative coevolution has played a significant role in improving standard evolution of neural networks by organizing the training problem into modules and independently solving them. The number of modules required to represent a neural network is critical to the success of evolution. This paper proposes a framework for the adaptation of the number of modules during evolution. The framework is called adaptive modularity cooperative coevolution. It is used for training recurrent neural networks on grammatical inference problems. The results shows that the proposed approach performs better than its counterparts as the dimensionality of the problem increases.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

References

  • Blanco A, Delgado M, Pegalajar MC (2001) A real-coded genetic algorithm for training recurrent neural networks. Neural Netw 14(1):93–105

    Article  MathSciNet  Google Scholar 

  • Brookshear JG (1989) Theory of computation: formal languages, automata, and complexity. Benjamin-Cummings Publishing Co., Inc., Redwood City

    MATH  Google Scholar 

  • Castao MA, Vidal E, Casacuberta F (1995) Finite state automata and connectionist machines: a survey. In: Mira J, Hernndez FS (eds) IWANN. Lecture Notes in Computer Science. Springer, New York, pp 433–440

  • Chandra R, Frean M, Zhang M (2010) An encoding scheme for cooperative coevolutionary feedforward neural networks. In: Li J (ed) AI 2010: advances in artificial intelligence. Lecture Notes in Computer Science, vol 6464. Springer, Berlin, pp 253–262

  • Chandra R, Frean M, Zhang M (2011a) Modularity adaptation in cooperative coevolutionary feedforward neural networks. In: International joint conference on neural networks, pp 681–688

  • Chandra R, Frean M, Zhang M, Omlin CW (2011b) Encoding subcomponents in cooperative co-evolutionary recurrent neural networks. Neurocomputing 74(17):3223–3234

    Article  Google Scholar 

  • Chandra R, Omlin CW (2006) Training and extraction of fuzzy finite state automata in recurrent neural networks. In: Proceedings of international conference on computational intelligence, pp 274–279

  • Chen W, Weise T, Yang Z, Tang K (2010) Large-scale global optimization using cooperative coevolution with variable interaction learning. In: Proceedings of the 11th international conference on Parallel problem solving from nature: Part II. PPSN’10, pp 300–309

  • Deb K, Anand A, Joshi D (2002) A computationally efficient evolutionary algorithm for real-parameter optimization. Evol Comput 10(4):371–395

    Article  Google Scholar 

  • Elman JL (1990) Finding structure in time. Cogn Sci 14:179–211

    Article  Google Scholar 

  • Gabrijel I, Dobnikar A (2003) On-line identification and reconstruction of finite automata with generalized recurrent neural networks. Neural Netw 16(1):101–120

    Article  Google Scholar 

  • García-Pedrajas N, Ortiz-Boyer D (2007) A cooperative constructive method for neural networks for pattern recognition. Pattern Recogn 40(1):80–98

    Article  MATH  Google Scholar 

  • Giles CL, Lawrence S, Tsoi A (1997) Rule inference for financial prediction using recurrent neural networks. In: Proceedings of the conference on computational intelligence for financial engineering, pp 253–259

  • Giles CL, Omlin C, Thornber KK (1999) Equivalence in knowledge representation: automata, recurrent neural networks, and dynamical fuzzy systems. Proc IEEE 87(9):1623–1640

    Article  Google Scholar 

  • Gomez F, Mikkulainen R (1997) Incremental evolution of complex general behavior. Adapt Behav 5(3–4):317–342

    Article  Google Scholar 

  • Gomez F, Schmidhuber J, Miikkulainen R (2008) Accelerated neural evolution through cooperatively coevolved synapses. J Mach Learn Res 9:937–965

    MathSciNet  MATH  Google Scholar 

  • Gomez FJ (2003) Robust non-linear control through neuroevolution. Technical Report AI-TR-03-303, PhD thesis, Department of Computer Science, The University of Texas at Austin

  • Haykin S, Principe J, Sejnowski T, McWhirter J (2006) New directions in statistical signal processing: from systems to brain. MIT Press, Cambridge

  • Kolen J, Kremer S (2001) A field guide to dynamical recurrent networks. IEEE Press, New Jersey

  • Li X, Yao X (2011) Cooperatively coevolving particle swarms for large scale optimization. IEEE Trans Evol Comput (in press)

  • Liu Y, Yao X, Zhao Q, Higuchi T (2001) Scaling up fast evolutionary programming with cooperative coevolution. In: Proceedings of the 2001 Congress on Evolutionary Computation, pp 1101–1108

  • Lozano M, Herrera F, Krasnogor N, Molina D (2004) Real-coded memetic algorithms with crossover hill-climbing. Evol Comput 12(3):273–302

    Article  Google Scholar 

  • Manolios P, Fanelli R (1994) First-order recurrent neural networks and deterministic finite state automata. Neural Comput 6(6):1155–1173

    Article  Google Scholar 

  • Marakami K, Taguchi H (1991) Gesture recognition using recurrent neural networks. In: Proceedings of the SIGCHI conference on Human factors in computing systems: reaching through technology, pp 237–242

  • Medsker L, Jain L (1999) Recurrent neural networks: design and application, Computer Intelligence. CRC Press international

  • Omidvar M, Li X, Yao X (2010) Cooperative co-evolution for large scale optimization through more frequent random grou**. In: 2010 IEEE Congress on evolutionary computation (CEC), pp 1754–1761

  • Omidvar MN, Li X, Yao X (2011) Smart use of computational resources based on contribution for cooperative co-evolutionary algorithms. In: Proceedings of the 13th annual conference on genetic and evolutionary computation. GECCO ’11, pp 1115–1122

  • Omlin CW, Thornber KK, Giles CL (1998) Fuzzy finite state automata can be deterministically encoded into recurrent neural networks. IEEE Trans Fuzzy Syst 6:76–89

    Article  Google Scholar 

  • Ong Y-S, Lim M-H, Zhu N, Wong K-W (2006) Classification of adaptive memetic algorithms: a comparative study. IEEE Trans Syst ManCybern Part B Cybern 36(1):141–152

    Article  Google Scholar 

  • Ortiz-Boyer D, HerváMartínez C, García-Pedrajas N (2005) Cixl2: a crossover operator for evolutionary algorithms based on population features. J Artif Int Res 24:1–48

    Article  MATH  Google Scholar 

  • Potter MA, De Jong KA (2000) Cooperative coevolution: an architecture for evolving coadapted subcomponents. Evol Comput 8(1):1–29

    Article  Google Scholar 

  • Potter MA, Jong KAD (1994) A cooperative coevolutionary approach to function optimization. In: PPSN III: proceedings of the international conference on evolutionary computation. The third conference on parallel problem solving from nature. Springer, London, UK, pp 249–257

  • Robinson T (1994) An application of recurrent nets to phone probability estimation. IEEE Trans Neural Netw 5:298–305

    Article  Google Scholar 

  • Salomon R (1996) Re-evaluating genetic algorithm performance under coordinate rotation of benchmark functions. A survey of some theoretical and practical aspects of genetic algorithms. Biosystems 39(3):263–278

    Article  Google Scholar 

  • Schmidhuber J, Wierstra D, Gagliolo M, Gomez F (2007) Training recurrent networks by evolino. Neural Comput 19(3):757–779

    Article  Google Scholar 

  • Shi Y-j, Teng H-f, Li Z-Q (2005) Cooperative co-evolutionary differential evolution for function optimization. In: Wang L, Chen K, Ong YS (eds) Advances in natural computation. Lecture Notes in Computer Science, vol 3611. Springer, Berlin, pp 1080–1088

  • Smith J (2007) Coevolving memetic algorithms: a review and progress report. IEEE Trans Syst Man Cybern Part B Cybern 37(1):6–17

    Article  Google Scholar 

  • Teo J, Hijazi HA, Omar ZA, Mohamad NR, Hamid Y (2007) Harnessing mutational diversity at multiple levels for improving optimization accuracy in g3-pcx. In: IEEE Congress on Evolutionary Computation. IEEE, New Jersey, pp 4502–4507. http://dblp.uni-trier.de/db/conf/cec/cec2007.html#TeoHOMH07

  • Tomita M (1982) Dynamic construction of finite automata from examples using hill-climbing. In: Proceedings of the fourth annual cognitive science conference. Ann Arbor Michigan, pp 105–108

  • van den Bergh F, Engelbrecht A (2004) A cooperative approach to particle swarm optimization. IEEE Trans Evol Comput 8(3):225–239

    Article  Google Scholar 

  • Watrous RL, Kuhn GM (1992) Induction of finite-state languages using second-order recurrent networks. Neural Comput 4(3):406–414

    Article  Google Scholar 

  • Yang Z, Tang K, Yao X (2008a) Large scale evolutionary optimization using cooperative coevolution. Inf Sci 178(15):2985–2999

    Article  MathSciNet  Google Scholar 

  • Yang Z, Tang K, Yao X (2008b) Multilevel cooperative coevolution for large scale optimization. In: IEEE congress on evolutionary computation, pp 1663–1670

Download references

Acknowledgments

The author expresses his sincere gratitude towards Mohammad Omidvar for an earlier discussion on the subject of this paper.

Author information

Authors and Affiliations

  1. School of Engineering and Computer Science, Victoria University of Wellington, P.O. Box 600, Wellington, 6140, New Zealand

    Rohitash Chandra, Marcus Frean & Mengjie Zhang

Authors
  1. Rohitash Chandra
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Marcus Frean
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mengjie Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Rohitash Chandra.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Chandra, R., Frean, M. & Zhang, M. Adapting modularity during learning in cooperative co-evolutionary recurrent neural networks. Soft Comput 16, 1009–1020 (2012). https://doi.org/10.1007/s00500-011-0798-9

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00500-011-0798-9

Keywords

Search

Navigation