Nonlinear Dynamics

, Volume 95, Issue 3, pp 1999–2017 | Cite as

A CNN-based neuromorphic model for classification and decision control

  • Paolo Arena
  • Marco Calí
  • Luca PatanéEmail author
  • Agnese Portera
  • Angelo G. Spinosa
Original Paper


In this paper, an insect brain-inspired computational structure was developed. The peculiarity of the core processing layer is the local connectivity among the spiking neurons, which allows for a representation under the cellular nonlinear network paradigm. Moreover, the processing layer works as a liquid state network with fixed internal connections and trainable output weights. Learning was accomplished by adopting a simple supervised, batch approach based on the calculation of the Moore–Penrose matrix. The architecture, taking inspiration from a specific neuropile of the insect brain, the mushroom bodies, is evaluated and compared with other standard and bio-inspired solutions present in the literature, referring to three different scenarios.


Cellular neural networks Insect brain Drosophila melanogaster Neural gas Mushroom bodies Classification Decision-making 



This study was funded by MIUR Project CLARA—Cloud platform for LAndslide Risk Assessment (Grant Number SNC_00451).

Compliance with ethical standards

Conflict of interest

The authors declare that they have no conflict of interest.


  1. 1.
    Agarap, A.F.M.: On breast cancer detection: an application of machine learning algorithms on the Wisconsin diagnostic dataset. In: Proceedings of the 2nd International Conference on Machine Learning and Soft Computing, ICMLSC ’18, pp. 5–9. ACM, New York (2018).
  2. 2.
    Aihan, T., Yalcin, M.E.: An application of small-world cellular neural networks on odor classification. Int. J. Bifurc. Chaos 22(01), 1250013 (2012). CrossRefGoogle Scholar
  3. 3.
    Anderson, M.: Neural reuse: a fundamental organizational principle of the brain. Behav. Brain Sci. 33(4), 245–266 (2010)CrossRefGoogle Scholar
  4. 4.
    Arena, E., Arena, P., Strauss, R., Patané, L.: Motor-skill learning in an insect inspired neuro-computational control system. Front. Neurorobot. 11, 12 (2017). CrossRefGoogle Scholar
  5. 5.
    Arena, P., Berg, C., Patané, L., Strauss, R., Termini, P.S.: Aninsect brain computational model inspired by Drosophila melanogaster: architecture description. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–7 (2010).
  6. 6.
    Arena, P., Caccamo, S., Patané, L., Strauss, R.: A computational model for motor learning in insects. In: IJCNN, Dallas, TX, pp. 1349–1356 (2013)Google Scholar
  7. 7.
    Arena, P., Caccamo, S., Patané, L., Strauss, R.: A computational model for motor learning in insects. In: International Joint Conference on Neural Networks (IJCNN), Dallas, TX, Aug 4–9, pp. 1349–1356 (2013)Google Scholar
  8. 8.
    Arena, P., Calí, M., Patané, L., Portera, A., Strauss, R.: Modeling the insect mushroom bodies: application to sequence learning. Neural Netw. 67, 37–53 (2015)CrossRefGoogle Scholar
  9. 9.
    Arena, P., Calí, M., Patané, L., Portera, A., Strauss, R.: A fly-inspired mushroom bodies model for sensory-motor control through sequence and subsequence learning. Int. J. Neural Syst. 26(6), 1650035 (2016)CrossRefGoogle Scholar
  10. 10.
    Arena, P., Castorina, S.M., Frasca, L.F., Ruta, M.: A CNN-based chip for robot locomotion control. ISCAS 3, 510–513 (2003)Google Scholar
  11. 11.
    Arena, P., Crucitti, P., Fortuna, L., Frasca, M., Lombardo, D., Patané, L.: Turing patterns in RD-CNNs for the emergence of perceptual states in roving robots. Bifurc. Chaos 17(1), 107–127 (2007)MathSciNetCrossRefzbMATHGoogle Scholar
  12. 12.
    Arena, P., Fiore, S.D., Patané, L., Pollino, M., Ventura, C.: Insect inspired unsupervised learning for tactic and phobic behavior enhancement in a hybrid robot. In: The 2010 International Joint Conference on Neural Networks (IJCNN), pp. 1–8 (2010).
  13. 13.
    Arena, P., Fortuna, L., Branciforte, M.: Reaction–diffusion CNN algorithms to generate and control artificial locomotion. IEEE Trans. Circuits Syst. I 46(2), 253–260 (1999)CrossRefGoogle Scholar
  14. 14.
    Arena, P., Patané, L.: Spatial Temporal Patterns for Action-Oriented Perception in Roving Robots II: An Insect Brain Computational Model. Cognitive Systems Monographs, vol. 21. Springer, Berlin (2014)CrossRefzbMATHGoogle Scholar
  15. 15.
    Arena, P., Patané, L., Strauss, R.: The insect mushroom bodies: a paradigm of neural reuse. In: ECAL, pp. 765–772. MIT Press, Taormina (2013)Google Scholar
  16. 16.
    Aso, Y., et al.: The neuronal architecture of the mushroom body provides a logic for associative learning. eLife 3, e04577 (2014). CrossRefGoogle Scholar
  17. 17.
    Baek, W., Ignizio, J.P.: Pattern classification via linear programming. Comput. Ind. Eng. 25(1), 393–396 (1993). CrossRefGoogle Scholar
  18. 18.
    Bako, L.: Real-time classification of datasets with hardware embedded neuromorphic neural networks. Brief. Bioinform. 11(3), 348–363 (2010)CrossRefGoogle Scholar
  19. 19.
    Barata, J.C.A., Hussein, M.S.: The Moore–Penrose Pseudoinverse. A Tutorial Review of the Theory. John Hopkins University Press, Baltimore (2013)Google Scholar
  20. 20.
    Barnstedt, O., David, O., Felsenberg, J., Brain, R., Moszynski, J., Talbot, C., Perrat, P., Waddell, S.: Memory-relevant mushroom body output synapses are cholinergic. Neuron 89(6), 1237–1247 (2017). CrossRefGoogle Scholar
  21. 21.
    Bel haj ali, W., Piro, P., Giampaglia, D., Pourcher, T., Bar laud, M.: Biological cells classification using bio-inspired descriptor in a boosting k-NN framework. In: 2012 25th IEEE International Symposium on Computer-Based Med ical Systems (CBMS), pp. 1–6 (2012).
  22. 22.
    Chang, H., Astolfi, A.: Gaussian based classification with application to the Iris data set. IFAC Proc. 44(1), 14271–14276 (2011)CrossRefGoogle Scholar
  23. 23.
    Chua, L.O., Roska, T.: The CNN paradigm. IEEE Trans. Circuits Syst. I Fundam. Theory Appl. 40(3), 147–156 (1993). CrossRefzbMATHGoogle Scholar
  24. 24.
    Dash, T., Sahu, S.R., Nayak, T., Mishra, G.: Neural network approach to control wall-following robot navigation. In: 2014 IEEE International Conference on Advanced Communications, Control and Computing Technologies, pp. 1072–1076 (2014).
  25. 25.
    Davis, R., Han, K.: Neuroanatomy: mushrooming mushroom bodies. Curr. Biol. 6, 146–148 (1996)CrossRefGoogle Scholar
  26. 26.
    Fisher, R.A.: The use of multiple measurement in taxonomic problems. Ann. Eugen. 7(2), 179–188 (1936). CrossRefGoogle Scholar
  27. 27.
    Freire, A.L., Barreto, G.A., Veloso, M., Varela, A.T.: Short-term memory mechanisms in neural network learning of robot navigation tasks: a case study. In: 2009 6th Latin American Robotics Symposium (LARS 2009), pp. 1–6 (2009).
  28. 28.
    Gerber, B., Tanimoto, H., Heisenberg, M.: An engram found? Evaluating the evidence from fruit flies. Curr. Opin. Neurobiol. 14, 737–744 (2004)CrossRefGoogle Scholar
  29. 29.
    Gorodkin, J.: Comparing two k-category assignments by a k-category correlation coefficient. Comput. Biol. Chem. 28(5–6), 367–374 (2004). CrossRefzbMATHGoogle Scholar
  30. 30.
    Gupta, N., Stopfer, M.: Functional analysis of a higher olfactory center, the lateral horn. J. Neurosci. 32(24), 8138–8148 (2012). CrossRefGoogle Scholar
  31. 31.
    Huerta, R., Nowotny, T., Garcia-Sanchez, M., Abarbanel, H., Rabinovich, M.: Learning classification in the olfactory system of insects. Neural Comput. 16(8), 1601–40 (2004)CrossRefzbMATHGoogle Scholar
  32. 32.
    Huerta, R., Vembu, S., Amigó, J.M., Nowotny, T., Elkan, C.: Inhibition in multiclass classification. Neural Comput. 24(9), 2473–2507 (2012)MathSciNetCrossRefzbMATHGoogle Scholar
  33. 33.
    Izhikevich, E.M.: Which model to use for cortical spiking neurons? IEEE Trans. Neural Netw. 15(5), 1063–1070 (2004)CrossRefGoogle Scholar
  34. 34.
    Jurman, G., Riccadonna, S., Furlanello, C.: A comparison of MCC and CEN error measures in multi-class prediction. PloS ONE 7(8), e41882 (2012). CrossRefGoogle Scholar
  35. 35.
    Kholerdi, H.A., TaheriNejad, N., Jantsch, A.: Enhancement of classification of small data sets using self-awareness—an Iris flower case-study. In: 2018 IEEE International Symposium on Circuits and Systems (ISCAS), pp. 1–5 (2018)Google Scholar
  36. 36.
    Leitch, B., Laurent, G.: Gabaergic synapses in the antennal lobe and mushroom body of the locust olfactory system. J. Comp. Neurol. 372(4), 487–514 (1996).<487::AID-CNE1>3.0.CO;2-0
  37. 37.
    Leitch, B., Laurent, G.: Gabaergic synapses in the antennal lobe and mushroom body of the locust olfactory system. J. Comp. Neurol. 372(4), 487–514 (1996)CrossRefGoogle Scholar
  38. 38.
    Leroy, F., Brann, D.H., Meira, T., Siegelbaum, S.A.: Input-timing-dependent plasticity in the hippocampal CA2 region and its potential role in social memory. Neuron 95(5), 1089–1102.e5 (2017). CrossRefGoogle Scholar
  39. 39.
    Maass, W., Markram, H.: On the computational power of circuits of spiking neurons. J. Comput. Syst. Sci. 69(4), 593–616 (2004). MathSciNetCrossRefzbMATHGoogle Scholar
  40. 40.
    Martinez, T., Schuten, K.: A neural-gas network learns topologies. Artif. Neural Netw. 1, 397–402 (1991)Google Scholar
  41. 41.
    Matsumoto, K., Mori, H., Uehara, M.: Fault tolerance in small world cellular neural networks for image processing. In: 21st International Conference on Advanced Information Networking and Applications Workshops, 2007, AINAW ’07, vol. 1, pp. 835–839 (2007).
  42. 42.
    Navarro, R., Acevedo, E., Acevedo, A., Martínez, F.: Associative model for solving the wall-following problem. In: Carrasco-Ochoa, J.A., Martínez-Trinidad, J.F., Olvera López, J.A., Boyer, K.L. (eds.) Pattern Recognition, pp. 176–186. Springer, Berlin (2012)CrossRefGoogle Scholar
  43. 43.
    Nowotny, T., Rabinovich, M., Huerta, R., Abarbanel, H.: Decoding temporal information through slow lateral excitation in the olfactory system of insects. J. Comput. Neurosci. 15, 271–281 (2003)CrossRefGoogle Scholar
  44. 44.
    Ooi, S.Y., Tan, S.C., Cheah, W.P.: Experimental Study of Elman Network in Temporal Classification, pp. 245–254. Springer, Singapore (2017)Google Scholar
  45. 45.
    Papamakarios, G.: Comparison of Modern Stochastic Optimization Algorithms. University of Edinburgh, Edinburgh (2014)Google Scholar
  46. 46.
    Perez-Orive, J., Mazor, O., Turner, G., Cassenaer, S., Wilson, R., Laurent, G.: Oscillations and sparsening of odor representations in the mushroom body. Science 297, 359–365 (2002)CrossRefGoogle Scholar
  47. 47.
    Sachse, S., Galizia, C.: Role of inhibition for temporal and spatial odor representation in olfactory output neurons: a calcium imaging study. J. Neurophysiol. 87, 1106–1117 (2002)CrossRefGoogle Scholar
  48. 48.
    Salama, G.I., Abdelhalim, M.B., Zeid, M.A.: Experimental comparison of classifiers for breast cancer diagnosis. In: 2012 Seventh International Conference on Computer Engineering Systems (ICCES), pp. 180–185 (2012).
  49. 49.
    Sathya, S., Joshi, S., Padmavathi, S.: Classification of breast cancer dataset by different classification algorithms. In: 2017 4th International Conference on Advanced Computing and Communication Systems (ICACCS), pp. 1–4 (2017).
  50. 50.
    Sboev, A., Vlasov, D., Rybka, R., Serenko, A.: Solving a classification task by spiking neurons with STDP and temporal coding. Procedia Comput. Sci. 123, 494–500 (2018)CrossRefGoogle Scholar
  51. 51.
    Schmuker, M., Pfeil, T., Nawrot, M.P.: A neuromorphic network for generic multivariate data classification. Proc. Natl. Acad. Sci. 111(6), 2081–2086 (2014). CrossRefGoogle Scholar
  52. 52.
    Schmuker, M., Schneider, G.: Processing and classification of chemical data inspired by insect olfaction. Proc. Natl. Acad. Sci. 104(51), 20285–20289 (2007). CrossRefGoogle Scholar
  53. 53.
    Shim, Y., Philippides, A., Staras, K., Husbands, P.: Unsupervised learning in an ensemble of spiking neural networks mediated by ITDP. PLOS Comput. Biol. 12(10), 1–41 (2016). CrossRefGoogle Scholar
  54. 54.
    Vogt, K., Aso, Y., Hige, T., Knapek, S., Ichinose, T., Friedrich, A.B., Turner, G.C., Rubin, G.M., Tanimoto, H.: Direct neural pathways convey distinct visual information to Drosophila mushroom bodies. eLife 5, e14009 (2016). CrossRefGoogle Scholar
  55. 55.
    Wang, J., Guo, P., Xin, X.: Review of pseudoinverse learning algorithm for multilayer neural networks and applications. In: Huang, T., Lv, J., Sun, C., Tuzikov, A.V. (eds.) Advances in Neural Networks—ISNN 2018, pp. 99–106. Springer, Cham (2018)CrossRefGoogle Scholar
  56. 56.
    Wolberg, W.H., Mangasarian, O.L.: Multisurface method of pattern separation for medical diagnosis applied to breast cytology. Proc. Natl. Acad. Sci. 87(23), 9193–9196 (1990)CrossRefzbMATHGoogle Scholar
  57. 57.
    Yang, J., Zhang, P., Liu, Y.: Robustness of classification ability of spiking neural networks. Nonlinear Dyn. 82(1), 723–730 (2015). MathSciNetCrossRefGoogle Scholar
  58. 58.
    Yavuz, E., Eyupoglu, C., Sanver, U., Yazici, R.: An ensemble of neural networks for breast cancer diagnosis. In: 2017 International Conference on Computer Science and Engineering (UBMK), pp. 538–543 (2017).
  59. 59.
    Zhou, L.: Global asymptotic stability of cellular neural networks with proportional delays. Nonlinear Dyn. 77(1), 41–47 (2014). MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer Nature B.V. 2018

Authors and Affiliations

  • Paolo Arena
    • 1
    • 2
  • Marco Calí
    • 1
  • Luca Patané
    • 1
    Email author
  • Agnese Portera
    • 1
  • Angelo G. Spinosa
    • 1
  1. 1.DIEEIUniversity of CataniaCataniaItaly
  2. 2.National Institute of Biostructures and Biosystems (INBB)RomeItaly

Personalised recommendations