Abstract
Computational neuroscience lays the foundations of intelligent behavior through the application of machine learning approaches. Brain programming, which derives from such approaches, is emerging as a new evolutionary computing paradigm for solving computer vision and pattern recognition problems. Primate brains have several distinctive features that are obtained by a complex arrangement of highly interconnected and numerous cortical visual areas. This paper describes a virtual system that mimics the complex structure of primate brains composed of an artificial dorsal pathway – or “where” stream – and an artificial ventral pathway – or “what” stream – that are fused to recreate an artificial visual cortex. The goal is to show that brain programming is able to discover numerous heterogeneous functions that are applied within a hierarchical structure of our virtual brain. Thus, the proposal applies two key ideas: first, object recognition can be achieved by a hierarchical structure in combination with the concept of function composition; second, the functions can be discovered through multiple random runs of the search process. This last point is important since is the first step in any evolutionary algorithm; in this way, enhancing the possibilities for solving hard optimization problems.
This is a preview of subscription content, log in via an institution.
References
Olague, G.: Evolutionary Computer Vision: The First Footprints. Springer, Heidelberg (2016)
Logothetis, N.K., Sheinberg, D.L.: Visual object recognition. Ann. Rev. Neurosci. 19, 577–621 (1996)
DiCarlo, J.J., Zoccolan, D., Rust, N.C.: How does the brain solve visual object recognition? Neuron 73(3), 415–434 (2012)
Riesenhuber, M., Poggio, T.: Models of object recognition. Nat. Neurosci. 3, 1199–1204 (2000)
Rees, G., Frackowiak, R., Frith, C.: Two modulatory effects of attention that mediate object categorization in human cortex. Science. 275(5301), 835–8 (1997)
Desimone, R., Duncan, J.: Neural mechanisms of selective visual attention. Ann. Rev. Neurosci. 18, 193–222 (1995)
Kastner, S., Ungerleider, L.G.: Mechanisms of visual attention in the human cortex. Ann. Rev. Neurosci. 23, 315–341 (2000)
Milner, A.D., Goodale, M.A.: The Visual Brain in Action, 2nd edn. Oxford University Press, Oxford (2006)
Creem, S.H., Proffitt, D.R.: Defining the cortical visual systems: “what”, “where”, and “how”. Acta Psychol. 107(1–3), 43–68 (2001)
Farivar, R.: Dorsal-ventral integration in object recognition. Brain Res. Rev. 61(2), 144–153 (2009)
Fukushima, K.: Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36(4), 193–202 (1980)
Serre, T., Kouh, C., Cadieu, M., Knoblich, G., Kreiman, U., Poggio, T.: Theory of object recognition: computations and circuits in the feedforward path of the ventral stream in primate visual cortex. Technical report, Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory (2005)
Mutch, J., Lowe, D.G.: Object class recognition and localization using sparse features with limited receptive fields. Int. J. Comput. Vis. 80(1), 45–57 (2008)
Mel, B.W.: Seemore: combining color, shape, and texture histogramming in a neurally inspired approach to visual object recognition. Neural Comput. 9(4), 777–804 (1997)
Itti, L., Koch, C.: Computational modeling of visual attention. Nat. Rev. Neurosci. 2(3), 194–203 (2001)
Clemente, E., Olague, G., Dozal, L., Mancilla, M.: Object recognition with an optimized ventral stream model using genetic programming. In: Chio, C., et al. (eds.) EvoApplications 2012. LNCS, vol. 7248, pp. 315–325. Springer, Heidelberg (2012). doi:10.1007/978-3-642-29178-4_32
Clemente, E., Olague, G., Dozal, L.: Purposive evolution for object recognition using an artificial visual cortex. In: Schuetze, O., Coello, C.A.C., Tantar, A.-A., Tantar, E., Bouvry, P., Del Moral, P., Legrand, P. (eds.) EVOLVE - A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation II, pp. 355–370. Springer, Heidelberg (2013)
Olague, G., Clemente, E., Dozal, L., Hernádez, D.E.: Evolving an artificial visual cortex for object recognition with brain programming. In: Schuetze, O., Coello, C.A.C., Tantar, A.-A., Tantar, E., Bouvry, P., Del Moral, P., Legrand, P., et al. (eds.) EVOLVE - A Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation III. Springer, Heidelberg (2014)
Dozal, L., Olague, G., Clemente, E., Hernandez, D.E.: Brain programming for the evolution of an articial dorsal stream. Cognit. Comput. 6(3), 528–557 (2014)
Hernandez, D.E., Clemente, E., Olague, G., Briseño, J.L.: Evolutionary multi-objective visual cortex for object classification in natural images. J. Comput. Sci. 17(1), 216–233 (2016)
Clemente, E., Chavez, F., Fernandez de Vega, F., Olague, G.: Self-adjusting focus of attention in combination with a genetic fuzzy system for improving a laser environment control device system. Appl. Soft Comput. 32, 250–265 (2015)
Fukushima, K.: Neural network model for selective attention in visual pattern recognition and associative recall. Appl. Opt. 26(23), 4985–4992 (1987)
Olshausen, B.A., Anderson, C.H., Van Essen, D.C.: A neurobiological model of visual attention and invariant pattern recognition based on dynamic routing of information. J. Neurosci. 13(11), 4700–4719 (1993)
Walther, D., Itti, L., Riesenhuber, M., Poggio, T., Koch, C.: Attentional selection for object recognition — a gentle way. In: Bülthoff, H.H., Wallraven, C., Lee, S.-W., Poggio, T.A. (eds.) BMCV 2002. LNCS, vol. 2525, pp. 472–479. Springer, Heidelberg (2002). doi:10.1007/3-540-36181-2_47
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2(11), 1019–1025 (1999)
Walther, D., Koch, C.: Attention in hierarchical models of object recognition. Progr. Brain Res. 165, 57–78 (2007)
Heinke, D., Humphteys, G.W.: Attention, spatial representation, and visual neglect: simulating emergent attention and spatial memory in the selective attention for identification model (SAIM). Psychol. Rev. 110(1), 29–87 (2003)
Treisman, A.M., Gelade, G.: A feature-integration theory of attention. Cogn. Psychol. 12(1), 97–136 (1980)
Walther, D., Koch, C.: Modeling attention to salient proto-objects. Neural Netw. 19(9), 1395–407 (2006)
Pinto, N., Cox, D.D., DiCarlo, J.J.: Why is real-world visual object recognition hard? PLoS Comput. Biol. 4(1), 151–156 (2008)
Ponce, J., et al.: Dataset issues in object recognition. In: Ponce, J., Hebert, M., Schmid, C., Zisserman, A. (eds.) Toward Category-Level Object Recognition. LNCS, vol. 4170, pp. 29–48. Springer, Heidelberg (2006). doi:10.1007/11957959_2
Wang, Z., Feng, J.: Multi-class learning from class proportions. Neurocomputing 119, 273–280 (2013)
Ji, Z., Wang, J., Su, Y., Song, Z., Xing, S.: Balance between object and background: object-enhanced features for scene image classification. Neurocomputing 120, 15–23 (2013)
Chen, B., Polatkan, G., Sapiro, G., Blei, D., Dunson, D., Carin, L.: Deep learning with hierarchical convolutional factor analysis. IEEE Trans. Pattern Anal. Mach. Intell. 8(35), 1887–1901 (2013)
Xu, B., Hu, R., Guo, P.: Combining affinity propagation with supervised dictionary learning for image classification. Neural Comput. Appl. 22(7–8), 1301–1308 (2013)
Chandra, S., Kumar, S., Jawahar, C.V.: Learning hierarchical bag of words using naive bayes clustering. In: Lee, K.M., Matsushita, Y., Rehg, J.M., Hu, Z. (eds.) ACCV 2012. LNCS, vol. 7724, pp. 382–395. Springer, Heidelberg (2013). doi:10.1007/978-3-642-37331-2_29
Wilcoxon, F.: Individual comparison by ranking methods. Biometr. Bull. 1(6), 80–83 (1945)
Massey, F.J.: The Kolmogorov-Smirnov test for goodness of fit. J. Am. Stat. Assoc. 46(253), 68–78 (1951)
Hernandez, D.E., Olague, G., Hernandez, B., Clemente, E.: CUDA-based parallelization of a bio-inspired model for fast object classification. Neural Comput. Appl. (2017). doi:10.1007/s00521-017-2873-3
Acknowledgments
This research was founded by CONACyT through the Project 155045 - “Programación cerebral aplicada al estudio del pensamiento y la visión”. This work is also supported by ITE-TecNM through the project 5748.16-P, “Optimización de controladores aplicados a la navegación de un robot móvil, utilizando cómputo evolutivo”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Olague, G., Clemente, E., Hernández, D.E., Barrera, A. (2017). Brain Programming and the Random Search in Object Categorization. In: Squillero, G., Sim, K. (eds) Applications of Evolutionary Computation. EvoApplications 2017. Lecture Notes in Computer Science(), vol 10199. Springer, Cham. https://doi.org/10.1007/978-3-319-55849-3_34
Download citation
DOI: https://doi.org/10.1007/978-3-319-55849-3_34
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-55848-6
Online ISBN: 978-3-319-55849-3
eBook Packages: Computer ScienceComputer Science (R0)