Abstract
Pyramidal neural networks (PNN) are computational systems inspired by the concept of receptive fields from the human visual system. These neural networks are designed for implicit feature extraction and have been applied in pattern recognition applications. In the original approach, the size of the receptive field within the same 2D layer is a constant parameter, while in the human visual system, the receptive field size is variable. This paper proposes a PNN with variable receptive fields determined by an evolutionary algorithm, called variable pyramidal neural network with evolutionary algorithms. We observed from experiments aiming at detecting faces in images that our approach can achieve better classification rates than the original PNN. We also observed that regions with more information (such as nose and eyes) are more emphasized by variable receptive fields. These results confirm the application of intelligent algorithms to determine adjustable receptive fields in neural networks is useful to find out relevant information for recognition task. Besides, the model is comparable to biological systems regarding the flexibility assigned to receptive fields.
Similar content being viewed by others
References
Bratton D, Kennedy J (2007) Defining a standard for particle swarm optimization. In: IEEE swarm intelligence symposium, pp 120–127
Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297. doi:10.1007/BF00994018
Deng L, Yu D (2014) Deep learning: methods and applications. Found Trends Signal Process 7(3–4):197–387. doi:10.1561/2000000039
Fernandes BJT, Cavalcanti GDC, Ren T (2013) Lateral inhibition pyramidal neural network for image classification. IEEE Trans Cybern 43:2082–2092
Ghosh K, Pal S (2010) Some insights into brightness perception of images in the light of a new computational model of figure-ground segregation. IEEE Trans Syst Man Cybern 40(4):758–766
Gilbert CD, Wiesel TN (1992) Receptive field dynamics in adult primary visual cortex. Nature 356(6365):150–152
Heisele B, Poggio T, Pontil M (2000) Face detection in still gray images. In: A.I. memo 1687, Center for Biological and Computational Learning
Lecun Y, Bottou L, Bengio Y, Haffner P (1998) Gradient-based learning applied to document recognition. In: Proceedings of the IEEE, vol 86, no 11, pp 2278–2324. doi:10.1109/5.726791. http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=726791
Levine M, Shefner J (2000) Fundamentals of sensation and perception. Oxford University Press, New York
Mao ZH, Massaquoi S (2007) Dynamics of winner-take-all competition in recurrent neural networks with lateral inhibition. IEEE Trans Neural Netw 18(1):55–69
Mitchell M (1998) An introduction to genetic algorithms. MIT Press, Cambridge
Pettet MW, Gilbert C (1992) Dynamic changes in receptive-field size in cat primary visual cortex. Proc Natl Acad Sci USA 89(17):8366–8370
Phung SL, Bouzerdoum A (2007) A pyramidal neural network for visual pattern recognition. IEEE Trans Neural Netw 18(2):329–343
Riedmiller M, Braun H (1993) A direct adaptive method for faster backpropagation learning: the RPROP algorithm. In: Proceedings of the IEEE international conference on neural networks, pp 586–591
Rizzolati G, Camarda R (1975) Inhibition of visual responses of single units in the cat visual area of the lateral suprasylvian gyrus (clare-bishop area) by the introduction of a second visual stimulus. Brain Res 88(2):357–361
Soares AM, Fernandes BJT, Bastos-Filho CJA (2014) Lateral inhibition pyramidal neural networks designed by particle swarm optimization. In: Wermter S, Weber C, Duch W, Honkela T, Koprinkova-Hristova P, Magg S, Palm G, Villa A (eds) Artificial neural networks and machine learning ICANN 2014, Lecture notes in computer science, vol 8681. Springer, pp 667–674
Acknowledgements
This research was partially supported by Brazilian agencies Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq), Coordenação de Aperfeiçoamento Pessoal de Nível Superior (CAPES) and Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco (FACEPE).
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Soares, A.M., Fernandes, B.J.T. & Bastos-Filho, C.J.A. Pyramidal neural networks with evolved variable receptive fields. Neural Comput & Applic 29, 1443–1453 (2018). https://doi.org/10.1007/s00521-016-2656-2
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-016-2656-2