Advertisement

Deep Learning with Random Neural Networks

  • Erol GelenbeEmail author
  • Yongha Yin
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 16)

Abstract

This paper develops multi-layer classifiers and auto-encoders based on the Random Neural Network. Our motivation is to build robust classifiers that can be used in systems applications such as Cloud management for the accurate detection of states that can lead to failures. Using an idea concerning some to soma interactions between natural neuronal cells, we discuss a basic building block constructed of clusters of densely packet cells whose mathematical properties are based on G-Networks and the Random Neural Network. These mathematical properties lead to a transfer function that can be exploited for large arrays of cells. Based on this mathematical structure we build multi-layer networks. In order to evaluate the level of classification accuracy that can be achieved, we test these auto-encoders and classifiers on a widely used standard database of handwritten characters.

Keywords

Random neural networks Deep learning G-Networks 

Notes

Acknowledgements

We gratefully acknowledge the support of the EC 7th Framework Program PANACEA Project, Grant Agreement No. 610764, to Imperial College London.

References

  1. 1.
    Doncel, J., Ayesta, U., Brun, O., Prabhu, B.: A resource-sharing game with relative priorities. In: IFIP Performance 2014, Turin, Italy (2014)Google Scholar
  2. 2.
    Sanzo, P.D., Pellegrini, A., Avresky, D.R.: Machine learning for achieving self-* properties and seamless execution of applications in the cloud. In: NCCA 2015, Munich, Germany. IEEE (2015)Google Scholar
  3. 3.
    Wang, L., Gelenbe, E.: Experiments with smart workload allocation to cloud servers. In: NCCA 2015. IEEE (2015)Google Scholar
  4. 4.
    Raina, R., Madhavan, A., Ng, A.: Large-scale deep unsupervised learning using graphics processors. In: Proceedings of 26th International Conference on Machine Learning (2009)Google Scholar
  5. 5.
    Ciresan, D.C., Meier, U., Gambardella, L.M., Schmidhuber, J.: Deep big simple neural nets for handwritten digit recognition. Neural Comput. 22, 3207–3220 (2010)CrossRefGoogle Scholar
  6. 6.
    Gerstner, W.: Spiking neurons. In: Maass, W., Bishop, C.M. (eds.) Pulsed Neural Networks. MIT Press, Cambridge (2001)Google Scholar
  7. 7.
    Gu, Y., Chen, Y., Zhang, X., Li, G.W., Wang, C.Y., Huang, L.-Y.M.: Neuronal soma-satellite glial cell interactions in sensory ganglia and the participation of purinergic receptors. Neuron Glia Biol. 6(1), 53–62 (2010)CrossRefGoogle Scholar
  8. 8.
    Krames, E.S., Peckham, P.H., Rezai, A.R. (eds.): Neuromodulation, vol. 1-2. Academic Press, Cambridge (2009)Google Scholar
  9. 9.
    Newman, E.A.: New roles for astrocytes: regulation of synaptic transmission. TRENDS Neurosci. 10(26), 536–542 (2001)Google Scholar
  10. 10.
    Arbib, M. (ed.): The Handbook of Brain Theory and Neural Networks. MIT Press, Cambridge (2003)zbMATHGoogle Scholar
  11. 11.
    Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. Nature 323, 533–536 (1986)CrossRefGoogle Scholar
  12. 12.
    Gelenbe, E.: Random neural networks with negative and positive signals and product form solution. Neural Comput. 1(4), 502–510 (1989)CrossRefGoogle Scholar
  13. 13.
    Gelenbe, E.: Learning in the recurrent random neural network. Neural Comput. 5, 154–164 (1993)CrossRefGoogle Scholar
  14. 14.
    Medhi, J.: Stochastic Processes. New Age International, Delhi (1994)zbMATHGoogle Scholar
  15. 15.
    Gelenbe, E., Cramer, C.: Oscillatory corticothalamic response to somatosensory input. Biosystems 48(1), 67–75 (1998)CrossRefGoogle Scholar
  16. 16.
    Gelenbe, E., Cao, Y.: Autonomous search for mines. Eu. J. Oper. Res. 108(2), 319–333 (1998)CrossRefzbMATHGoogle Scholar
  17. 17.
    Gelenbe, E., Koçak, T.: Area-based results for mine detection. IEEE Trans. Geosci. Remote Sens. 38(1), 12–24 (2000)CrossRefGoogle Scholar
  18. 18.
    Cramer, C., Gelenbe, E., Bakircloglu, H.: Low bit-rate video compression with neural networks and temporal subsampling. Proc. IEEE 84(10), 1529–1543 (1996)CrossRefGoogle Scholar
  19. 19.
    Cramer, C.E., Gelenbe, E.: Video quality and traffic qos in learning-based subsampled and receiver-interpolated video sequences. IEEE J. Sel. Areas Commun. 18(2), 150–167 (2000)CrossRefGoogle Scholar
  20. 20.
    Abdelbaki, H.M., Hussain, K., Gelenbe, E.: A laser intensity image based automatic vehicle classification system. In: Proceedings of Intelligent Transportation Systems, pp. 460–465. IEEE (2001)Google Scholar
  21. 21.
    Gelenbe, E., Koubi, V., Pekergin, F.: Dynamical random neural network approach to the traveling salesman problem. In: Proceedings IEEE Symposium on Systems, Man and Cybernetics, pp. 630–635. IEEE (1993)Google Scholar
  22. 22.
    Gelenbe, E., Kazhmaganbetova, Z.: Cognitive packet network for bilateral asymmetric connections. IEEE Trans. Ind. Inform. 10(3), 1717–1725 (2014). doi: 10.1109/TII.2014.2321740 CrossRefGoogle Scholar
  23. 23.
    Gelenbe, E., Wu, F.-J.: Large scale simulation for human evacuation and rescue. Comput. Math. Appl. 64(12), 3869–3880 (2012)CrossRefGoogle Scholar
  24. 24.
    Gelenbe, E., Fourneau, J.-M.: Random neural networks with multiple classes of signals. Neural Comput. 11(4), 953–963 (1999)CrossRefGoogle Scholar
  25. 25.
    Gelenbe, E., Timotheou, S.: Random neural networks with synchronized interactions. Neural Comput. 20(9), 2308–2324 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  26. 26.
    Gelenbe, E.: The first decade of g-networks. Eu. J. Oper. Res. 126(2), 231–232 (2000)MathSciNetCrossRefzbMATHGoogle Scholar
  27. 27.
    Tang, J., Deng, C., Huang, G.-B.: Extreme learning machine for multilayer perceptron. IEEE Trans. Neurla Netw. Learn. Syst. May 2015 (to appear)Google Scholar
  28. 28.
    Kasun, L.L.C., Zhou, H., Huang, G.-B.: Representational learning with extreme learning machine for big data. IEEE Intell. Syst. 28(6), 31–34 (2013)Google Scholar
  29. 29.
    Beck, A., Teboulle, M.: A fast iterative shrinkage-thresholding algorithm for linear inverse problems. SIAM J. Imag. Sci. 2(1), 183–202 (2009)MathSciNetCrossRefzbMATHGoogle Scholar
  30. 30.
    LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)CrossRefGoogle Scholar
  31. 31.
    Wang, L., Gelenbe, E.: Adaptive dispatching of tasks in the cloud. IEEE Trans. Cloud Comput. (2015)Google Scholar
  32. 32.
    Brun, O., Wang, L., Gelenbe, E.: Data driven smart intercontinental overlay networks. IEEE Trans. Sel. Areas Commun. (2016)Google Scholar

Copyright information

© Springer International Publishing AG 2018

Authors and Affiliations

  1. 1.Intelligent Systems and Networks Group, Electrical and Electronic Engineering DepartmentImperial CollegeLondonUK

Personalised recommendations