Abstract
Artificial neural networks, especially for deep learning, has made great progress in image recognition in recent years. However, deep learning neural networks have the disadvantage of biologically implausibility and the excessive consumption of energy because of the non-local transmission of real-valued error signals and weights. With the rapid development of theories and applications in brain science, more and more researchers are paying attention to brain-inspired computational models in recent years. In this paper, we propose a novel computational model for image classification with conceptor networks and two visual cortex neural networks, including the primary visual layer (V1) and the feature orientation layer (V2). We have examined the performance of this model on the MNIST database, ORL face databases and CASIA-3D FaceV1 databases. Our model can achieve the same high classification accuracy with much fewer training samples than the other methods. Our results demonstrate that both of the orientation-selective characteristics of V2 layer and the feature detection of conceptors can provide remarkable contributions for efficient classification with small training samples.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. CoRR, vol. abs/1502.03167 (2015)
Ng, J.Y.-H., Hausknecht, M., Vijayanarasimhan, S., Vinyals, O., Monga, R., Toderici, G.: Beyond short snippets: deep networks for video classification. CoRR, vol. abs/1503.08909 (2015)
Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. CoRR, vol. abs/1503.03832 (2015)
Szegedy, C., et al.: Going deeper with convolutions. CoRR, vol. abs/1409.4842 (2014)
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529–533 (2015)
Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., FeiFei, L.: Large-scale video classification with convolutional neural networks. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)
Bishop, C.: Pattern Recognition and Machine Learning, pp. 140–155. Springer, New York (2006)
Chang, C.-C., Lin, C.-J.: Libsvm: a library for support vector machines. ACM Trans. Intel. Syst. Technol. 2(3), 1–27 (2011)
Mohamed, A.-R., Dahl, G.E., Hinton, G.: Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Language Process. 20(1), 14–22 (2012)
Rumelhart, D.E., Hinton, G.E., Williams, R.J., et al.: Learning representations by back-propagating errors. Cognit. Model. 5(3), 1 (1988)
OReilly, R.C., Munakata, Y.: Computational Explorations in Cognitive Neuroscience: Understanding the Mind by Simulating the Brain. MIT Press, Cambridge (2000)
Bogler, C., Bode, S., Haynes, J.D.: Orientation pop-out processing in human visual cortex. Neuroimage 81(6), 73–80 (2013)
Simoncelli, E.P., Heeger, D.J.: A model of neuronal responses in visual area MT. Vis. Res. 38(5), 743–761 (1998)
Miller, C.E., Shapiro, K.L., Luck, S.J.: Electrophysiological measurement of the effect of inter-stimulus competition on early cortical stages of human vision. Neuroimage 105, 229–237 (2015)
Beyeler, M., Richert, M., Dutt, N.D., et al.: Efficient spiking neural network model of pattern motion selectivity in visual cortex. Neuroinformatics 12(3), 435–454 (2014)
Kamitani, Y., Tong, F.: Decoding seen and attended motion directions from activity in the human visual cortex. Curr. Biol. 16(11), 1096–1102 (2006)
Kamitani, Y., Tong, F.: Decoding the visual and subjective contents of the human brain. Nat. Neurosci. 8(5), 679–685 (2005)
Beyeler, M., Oros, N., Dutt, N., et al.: A GPU-accelerated cortical neural network model for visually guided robot navigation. Neural Netw. 72, 75–87 (2015)
Richert, M., Nageswaran, J.M., Dutt, N., et al.: An efficient simulation environment for modeling large-scale cortical processing. Front. Neuroinform. 5(19), 19 (2011)
Beyeler, M., Dutt, N.D., Krichmar, J.L.: Categorization and decision-making in a neurobiologically plausible spiking network using a STDP-like learning rule. Neural Netw. 48(10), 109–124 (2013)
Jaeger, H., Haas, H.: Harnessing nonlinearity: Predicting chaotic systems and saving energy in wireless communication. Science 304(5667), 78–80 (2004)
Jaeger, H.: Using conceptors to manage neural long-term memories for temporal patterns. J. Mach. Learn. Res. 18(13), 1–43 (2017)
Izhikevich, E.M.: Simple model of spiking neurons. IEEE Trans. Neural Netw. 14, 1569–1572 (2003)
Dayan, P., Abbott, L.: Theoretical neuroscience: computational and mathematical modeling of neural systems. Philos. Psychol. 15(1), 154–155 (2001)
Izhikevich, E.M., Gally, J.A., Edelman, G.M.: Spike-timing dynamics of neuronal groups. Cereb. Cortex 14(8), 933–944 (2004)
Koch, C.: Biophysics of Computation: Information Processing in Single Neurons Computational Neuroscience Series. Oxford University Press, Oxford (1999)
Jaeger, H.: Controlling recurrent neural networks by conceptors (2014). arXiv:1403.3369
Diehl, P.U., Neil, D., Binas, J., et al.: Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: International Joint Conference on Neural Networks, pp. 1–8. IEEE (2015)
Peter, O., Daniel, N., Liu, S.C., et al.: Real-time classification and sensor fusion with a spiking deep belief network. Front. Neurosci. 7(7), 178 (2013)
Hu, Y., Ishwarya, M.S., Chu, K.L.: Classify images with conceptor network. Comput. Sci. (2015)
Qi, Y., Zhang, J.: (2D)2PCALDA: An Efficient Approach for Face Recognition. Elsevier Science Inc., Amsterdam (2009)
Kim, Y.G., Song, Y.J., Chang, U.D., et al.: Face recognition using a fusion method based on bidirectional 2DPCA. Appl. Math. Comput.. 205(2), 601–607 (2008)
Guo, G., Li, S.Z., Chan, K.: Proceedings of the Face Recognition by Support Vector Machines IEEE International Conference on Automatic Face and Gesture Recognition, 2000, pp. 196–201. IEEE (2002)
Li, G., Zhou, B., Su, Y.N.: Face recognition algorithm using two dimensional locality preserving projection in discrete wavelet domain. Open Automat. Contr. Syst. J. 7(1), 1721–1728 (2015)
Braitenberg, V., Schz, A.: Cortex: Statistics and Geometry of Neuronal Connectivity. Springer, Heidelberg (1998)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Li, X., Yu, J., Xu, W. (2021). A Computational Model Based on Neural Network of Visual Cortex with Conceptors for Image Classification. In: Zhang, H., Yang, Z., Zhang, Z., Wu, Z., Hao, T. (eds) Neural Computing for Advanced Applications. NCAA 2021. Communications in Computer and Information Science, vol 1449. Springer, Singapore. https://doi.org/10.1007/978-981-16-5188-5_9
Download citation
DOI: https://doi.org/10.1007/978-981-16-5188-5_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-5187-8
Online ISBN: 978-981-16-5188-5
eBook Packages: Computer ScienceComputer Science (R0)