ArticlesNo Access

ON THE PROBABILISTIC OPTIMIZATION OF SPIKING NEURAL NETWORKS

STEFAN SCHLIEBS

Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand

Search for more papers by this author

NIKOLA KASABOV

Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand

Search for more papers by this author

, and

MICHAËL DEFOIN-PLATEL

Department of Biomathematics and Bioinformatics, Rothamsted Research, United Kingdom

Search for more papers by this author

https://doi.org/10.1142/S0129065710002565Cited by:39 (Source: Crossref)

Abstract

The construction of a Spiking Neural Network (SNN), i.e. the choice of an appropriate topology and the configuration of its internal parameters, represents a great challenge for SNN based applications. Evolutionary Algorithms (EAs) offer an elegant solution for these challenges and methods capable of exploring both types of search spaces simultaneously appear to be the most promising ones. A variety of such heterogeneous optimization algorithms have emerged recently, in particular in the field of probabilistic optimization. In this paper, a literature review on heterogeneous optimization algorithms is presented and an example of probabilistic optimization of SNN is discussed in detail. The paper provides an experimental analysis of a novel Heterogeneous Multi-Model Estimation of Distribution Algorithm (hMM-EDA). First, practical guidelines for configuring the method are derived and then the performance of hMM-EDA is compared to state-of-the-art optimization algorithms. Results show hMM-EDA as a light-weight, fast and reliable optimization method that requires the configuration of only very few parameters. Its performance on a synthetic heterogeneous benchmark problem is highly competitive and suggests its suitability for the optimization of SNN.

Keywords:

References

W. Maass, Pulsed Neural Networks (MIT Press, Cambridge, MA, USA, 1999) pp. 55–85. Google Scholar
W. Gerstner and W. M. Kistler , Spiking Neuron Models: Single Neurons, Populations, Plasticity ( Cambridge University Press , Cambridge, MA , 2002 ) . Crossref, Google Scholar
S. Ghosh-Dastidar and H. Adeli, Advances in Computational Intelligence, Advances in Soft Computing 116, eds. W. Yu and E. Sanchez (Springer, Berlin/Heidelberg, 2009) pp. 167–178. Crossref, Google Scholar
S. Ghosh-Dastidar and H. Adeli, Int. J. Neural Syst. 19(4), 295 (2009), DOI: 10.1142/S0129065709002002. Link, Web of Science, Google Scholar
D. Verstraeten, B. Schrauwen and D. Stroobandt, Isolated word recognition using a liquid state machine, ESANN (2005) pp. 435–440. Google Scholar
S. M. Bohte, J. N. Kok and J. A. L. Poutré, Neurocomputing 48(4), 17 (2002), DOI: 10.1016/S0925-2312(01)00658-0. Crossref, Web of Science, Google Scholar
F. Ponulak, ReSuMe–new supervised learning method for spiking neural networks, Tech. Rep., Institute of Control and Information Engineering, Poznań University of Technology, Poznań, Poland (2005) . Google Scholar
A. Knoblauch, Inf. Process. Lett. 95(6), 537 (2005), DOI: 10.1016/j.ipl.2005.05.021. Crossref, Web of Science, Google Scholar
N. Iannella and L. Kindermann, Information Processing Letters 95(6), 545 (2005), DOI: 10.1016/j.ipl.2005.05.022. Crossref, Web of Science, Google Scholar
J. Iglesias and A. E. Villa, Int. J. Neural Syst. 18(4), 267 (2008), DOI: 10.1142/S0129065708001580. Link, Web of Science, Google Scholar
J. L. Rossellóet al., Int. J. Neural Syst. 19(6), 465 (2009). Link, Web of Science, Google Scholar
S. Ghosh-Dastidar and H. Adeli, Integr. Comput.-Aided Eng. 14(3), 187 (2007). Crossref, Web of Science, Google Scholar
S. Ghosh-Dastidar and H. Adeli, Neural Networks 22(10), 1419 (2009), DOI: 10.1016/j.neunet.2009.04.003. Crossref, Medline, Web of Science, Google Scholar
N. Pavlidiset al., Spiking neural network training using evolutionary algorithms, Proc. of International Joint Conference on Neural Networks (IJCNN'05) (2005) pp. 2190–2194. Google Scholar
C. Taylor and A. Agah, Evolving neural network topologies for object recognition, Automation Congress, 2006. WAC'06 (IEEE, Budapest, Hungary, 2006) pp. 1–6. Google Scholar
S. Schliebset al., Neural Networks 22(6), 623 (2009), DOI: 10.1016/j.neunet.2009.06.038. Crossref, Medline, Web of Science, Google Scholar
K. Hintz and J. Spofford, Evolving a neural network, 5th IEEE International Symposium on Intelligent Control1 (1990) pp. 479–484. Google Scholar
V. Maniezzo, IEEE Transactions on Neural Networks 5(1), 39 (1994), DOI: 10.1109/72.265959. Crossref, Medline, Web of Science, Google Scholar
F. Leunget al., IEEE Transactions on Neural Networks 14(1), 79 (2003), DOI: 10.1109/TNN.2002.804317. Crossref, Medline, Web of Science, Google Scholar
D. White and P. A. Ligomenides, GANNet: A genetic algorithm for optimizing topology and weights in neural network design, IWANN'93: Proceedings of the International Workshop on Artificial Neural Networks (Springer-Verlag, London, UK, 1993) pp. 322–327. Google Scholar
E. Alba, J. F. A. Montes and J. M. Troya, Full automatic ANN design: A genetic approach, IWANN'93: Proceedings of the International Workshop on Artificial Neural Networks (Springer-Verlag, London, UK, 1993) pp. 399–404. Google Scholar
S. Oliker, M. Furst and O. Maimon, Design architectures and training of neural networks with a distributed genetic algorithm, IEEE International Conference on Neural Networks1 (1993) pp. 199–202. Google Scholar
S. Hung and H. Adeli, Neural Networks, IEEE Transactions 5(6), 900 (1994), DOI: 10.1109/72.329686. Crossref, Web of Science, Google Scholar
M. Valko, N. C. Marques and M. Castelani, Evolutionary feature selection for spiking neural network pattern classifiers, Proceedings of 2005 Portuguese Conference on Artificial Intelligence (IEEE Press, 2005) pp. 24–32. Google Scholar
M. Castellani and N. Marques, VIMation Journal 1, 46 (2008). Google Scholar
M. Castellani and H. Rowlands, Engineering Applications of Artificial Intelligence 22(5), 732 (2009), DOI: 10.1016/j.engappai.2009.01.013. Crossref, Web of Science, Google Scholar
M. Castellani, ANNE — A new algorithm for evolution of artificial neural network classifier systems, IEEE Congress on Evolutionary Computation, CEC'06 (2006) pp. 3294–3301. Google Scholar
D. Riveroet al., A genetic algorithm for ANN design, training and simplification, IWANN'09: Proceedings of the 10th International Work-Conference on Artificial Neural Networks (Springer-Verlag, Berlin, Heidelberg, 2009) pp. 391–398. Google Scholar
B. A. Garro, H. Sossa and R. A. Vazquez, Design of artificial neural networks using a modified particle swarm optimization algorithm, International Joint Conference on Neural Networks, IEEE - INNS - ENNS (2009) pp. 938–945. Google Scholar
J. Ocenasek and J. Schwarz, Estimation of distribution algorithm for mixed continuous-discrete optimization problems, 2nd Euro-International Symposium on Computational Intelligence (IOS Press, Kosice, Slovakia, 2002) pp. 227–232. Google Scholar
S. Kernet al., Natural Computing 3(1), 77 (2004), DOI: 10.1023/B:NACO.0000023416.59689.4e. Crossref, Google Scholar
J. Ocenasek, Parallel estimation of distribution algorithms. Ph.D. thesis, Faculty of Information Technology, Brno University of Technology, Brno, Czech Rep. (2002) . Google Scholar
K. Socha, ACO for continuous and mixed-variable optimization, Ant Colony, Optimization and Swarm Intelligence (2004) pp. 25–36. Google Scholar
O. Cordónet al., A new ACO model integrating evolutionary computation concepts: The best-worst ant system, From Ant Colonies to Artificial Ants: Proceedings of the Second International Workshop on Ant Algorithms, eds. M. Dorigo, M. Middendoff and T. Stützle (Springer, Brussels, Belgium, 2000) pp. 22–29. Google Scholar
N. Monmarché, E. Ramat, G. Dromel, M. Slimane and G. Venturini, On the similarities between AS, BSC and PBIL: Toward the birth of a new meta-heuristic, Rapport Interne 215, Laboratoire d'Informatique de l'Université de Tours, E3i Tours (1999) . Google Scholar
S. Schliebs, M. Defoin-Platel and N. Kasabov, Advances in Neuro-Information Processing, 15th International Conference5506, Lecture Notes in Computer Science, eds. M. Köppen, N. K. Kasabov and G. G. Coghill (Springer, Heidelberg, Germany, 2009) pp. 1229–1236. Google Scholar
M. Defoin-Platel, S. Schliebs and N. Kasabov, A versatile quantum-inspired evolutionary algorithm, IEEE Congress on Evolutionary Computation, CEC'07 (IEEE Press, Singapore, 2007) pp. 423–430. Google Scholar
S. G. Wysoski, L. Benuskova and N. Kasabov, On-line learning with structural adaptation in a network of spiking neurons for visual pattern recognition, Artificial Neural Networks ICANN 2006 (Springer, Berlin/Heidelberg, 2006) pp. 61–70. Google Scholar
M. Defoin-Platel, S. Schliebs and N. Kasabov, Evolutionary Computation, IEEE Transactions 13(6), 1218 (2009). Crossref, Web of Science, Google Scholar
R. Kohavi and G. H. John, Artificial Intelligence 97(2), 273 (1997), DOI: 10.1016/S0004-3702(97)00043-X. Crossref, Web of Science, Google Scholar
S. Schliebset al., Quantum-inspired feature and parameter optimisation of evolving spiking neural networks with a case study from ecological modeling, International Joint Conference on Neural Networks, IEEE - INNS - ENNS (IEEE Computer Society, Los Alamitos, CA, USA, 2009) pp. 2833–2840. Google Scholar
S. Schliebs , M. Defoin-Platel and N. Kasabov , Analyzing the dynamics of the simultaneous feature and parameter optimization of an evolving spiking neural network , International Joint Conference on Neural Networks, IEEE - INNS - ENNS ( IEEE Computer Society , Barcelona, Spain , 2010 ) . Google Scholar
S. Schliebs, Heterogeneous Probabilistic Models for Optimisation and Modelling of Evolving Spiking Neural Networks. Ph.D. thesis, Auckland University of Technology (2010). http://hdl.handle.net/10292/963 . Google Scholar
P. Larrañaga and J. A. Lozano , Estimation of Distribution Algorithms: A New Tool for Evolutionary Computation ( Kluwer Academic Publishers , Boston , 2002 ) . Crossref, Google Scholar
J. Geweke, Efficient simulation from the multivariate normal and student-t distributions subject to linear constraints and the evaluation of constraint probabilities, Computing Science and Statistics: Proceedings of the 23rd Symposium on the Interface (American Statistical Association, New York, Seattle, Washington, 1991) pp. 571–578. Google Scholar
K.-H. Han and J.-H. Kim, On setting the parameters of quantum-inspired evolutionary algorithm for practical application, Congress on Evolutionary Computation, CEC'031 (IEEE Press, Canberra, Australia, 2003) pp. 178–194. Google Scholar
D. Thierens, D. Goldberg and A. Pereira, Domino convergence, drift, and the temporal-salience structure of problems, Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence (IEEE Press, 1998) pp. 535–540. Google Scholar
W. M. Rudnick, Genetic Algorithms and Fitness Variance with an Application to the Automated Design of Artificial Neural Networks. Ph.D. thesis, Oregon Graduate Institute of Science & Technology, Beaverton, OR, USA (1992) . Google Scholar
K.-H. Han and J.-H. Kim, IEEE Transactions on Evolutionary Computation 8(2), 156 (2004), DOI: 10.1109/TEVC.2004.823467. Crossref, Web of Science, Google Scholar
H. Mühlenbein and G. Paass, From recombination of genes to the estimation of distributions I. binary parameters, PPSN (1996) pp. 178–187. Google Scholar
S. Baluja, Population-based incremental learning: A method for integrating genetic search based function optimization and competitive learning, Tech. Rep. CMU-CS-94-163, Carnegie Mellon University, Pittsburgh, PA (1994) . Google Scholar
G. R. Harik, F. G. Lobo and D. E. Goldberg, IEEE Transactions on Evolutionary Computation 3(4), 287 (1999), DOI: 10.1109/4235.797971. Crossref, Web of Science, Google Scholar
Z. Michalewicz and C. Z. Janikow, Statistics and Computing 1(2), 75 (1991), DOI: 10.1007/BF01889983. Crossref, Google Scholar
A. Auger and N. Hansen, Performance evaluation of an advanced local search evolutionary algorithm, IEEE Congress on Evolutionary Computation2 (IEEE Press, 2005) pp. 1777–1784. Google Scholar
P. N. Suganthan, N. Hansen, J. J. Liang, K. Deb, Y. P. Chen, A. Auger and S. Tiwari, Problem definitions and evaluation criteria for the CEC 2005 special session on real parameter optimization, Tech. Rep., Nanyang Technological University, Singapore (2005) . Google Scholar
M. A. Potter and K. A. D. Jong, Evolutionary Computation 8, 1 (2000), DOI: 10.1162/106365600568086. Crossref, Medline, Web of Science, Google Scholar
N. Kasabov, Neural Networks 23(1), 16 (2010), DOI: 10.1016/j.neunet.2009.08.010. Crossref, Medline, Web of Science, Google Scholar
L. Benuskova and N. Kasabov , Computational Neurogenetic Modeling ( Springer , NY , 2007 ) . Crossref, Google Scholar
L. Benuskovaet al., Intl. Journal of Neural Systems 16(3), 215 (2006), DOI: 10.1142/S0129065706000627. Link, Web of Science, Google Scholar