Abstract
Some strategies used by the insect olfactory system to enhace its discrimination capability are an heterogeneous neural threshold distribution, gain control and sparse activity. To test the influence of these mechanisms on the performance for a classification task, we propose a neural network based on the insect olfactory system. In this model, we introduce a regulation term to control de activity of neurons and a structured connectivity between antennal lobe and mushroom body based on recent findings in Drosophila that differs from the classical stochastic approach. Results show that the model achieves better results for high sparseness and low connectivity between Kenyon cells and projection neurons. For this configuration, the use of gain control further improves performance. The structured connectivity model proposed is able to achieve the same discrimination capacity without using gain control or activiy regulation techniques, which opens up interesting possibilities.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
MNIST handwritten digit database. http://yann.lecun.com/exdb/mnist/
Eichler, K., et al.: The complete connectome of a learning and memory centre in an insect brain. Nature 548(7666), 175–182 (2017)
García-Sanchez, M., Huerta, R.: Design parameters of the fan-out phase of sensory systems. J. Comput. Neurosci. 15(1), 5–17 (2003)
Huerta, R., Nowotny, T.: Fast and robust learning by reinforcement signals: explorations in the insect brain. Neural Comput. 21(8), 2123–2151 (2009)
Huerta, R., Nowotny, T., García-Sanchez, M., Abarbanel, H.D.I., Rabinovich, M.I.: Learning classification in the olfactory system of insects. Neural Comput. 16(8), 1601–1640 (2004)
Jortner, R.A., Farivar, S.S., Laurent, G.: A simple connectivity scheme for sparse coding in an olfactory system. J. Neurosci. 27(7), 1659–1669 (2007)
Kaupp, U.B.: Olfactory signalling in vertebrates and insects: differences and commonalities. Nature Rev. Neurosci. 11(3), 188–200 (2010)
Montero, A., Huerta, R., Rodríguez, F.B.: Neuron threshold variability in an olfactory model improves odorant discrimination. In: Ferrández Vicente, J.M., Álvarez Sánchez, J.R., de la Paz López, F., Toledo Moreo, F.J. (eds.) IWINAC 2013. LNCS, vol. 7930, pp. 16–25. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-38637-4_3
Montero, A., Huerta, R., Rodríguez, F.B.: Regulation of specialists and generalists by neural variability improves pattern recognition performance. Neurocomputing 151(Part 1), 69–77 (2015)
Montero, A., Huerta, R., Rodríguez, F.B.: Stimulus space complexity determines the ratio of specialist and generalist neurons during pattern recognition. J. Frankl. Inst. 355, 2951–2977 (2018)
Perez-Orive, J., Mazor, O., Turner, G.C., Cassenaer, S., Wilson, R.I., Laurent, G.: Oscillations and sparsening of odor representations in the mushroom body. Science 297(5580), 359–365 (2002)
Rubin, B.D., Katz, L.C.: Optical imaging of odorant representations in the mammalian olfactory bulb. Neuron 23(3), 499–511 (1999)
Scardapane, S., Wang, D.: Randomness in neural networks: an overview. Wiley Interdiscip. Rev.: Data Min. Knowl. Discov. 7(2), e1200 (2017)
Serrano, E., Nowotny, T., Levi, R., Smith, B.H., Huerta, R.: Gain control network conditions in early sensory coding. Plos Comput. Biol. 9(7), e1003133 (2013)
Acknowledgments
We thank Ramon Huerta for his useful discussions. We acknowledge support from MINECO/FEDER TIN2014-54580-R and TIN2017-84452-R (http://www.mineco.gob.es/).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer Nature Switzerland AG
About this paper
Cite this paper
Lopez-Hazas, J., Montero, A., Rodriguez, F.B. (2018). Strategies to Enhance Pattern Recognition in Neural Networks Based on the Insect Olfactory System. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds) Artificial Neural Networks and Machine Learning – ICANN 2018. ICANN 2018. Lecture Notes in Computer Science(), vol 11139. Springer, Cham. https://doi.org/10.1007/978-3-030-01418-6_46
Download citation
DOI: https://doi.org/10.1007/978-3-030-01418-6_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-01417-9
Online ISBN: 978-3-030-01418-6
eBook Packages: Computer ScienceComputer Science (R0)