Abstract
In 1949, Donald Hebb proposed its Neurophysiologic Principle, which models the weight change of connected neurons. Although similar mechanisms have been experimentally proven to exists in several brain areas, traditional Deep Learning methods do not implement it, generally using Gradient-based algorithms instead. On the other hand, Convolutional Neural Networks (CNNs) has slight inspiration on the structure of Visual Cortex, particularly on the Hierarchical model of Hubel-Wiesel. Using convolutional layers it is possible to perform feature extraction and a final classification with dense layers. In this paper, we propose a combined technique of using pre-trained convolutional layers and a final classification using Hebbian-based rules (Basic Hebb, Covariance, Oja, and BCM). Once the feature extraction is done, Hebbian rules can discriminate the classes with high accuracy. These theoretical ideas were tested using this MNIST database, reaching 99.43% of test accuracy training CNNs layers with a final Hebb layer. Similar results were found using Hebbian-based rules in other datasets with RGB images and Transfer Learning. Even when these results are slightly lower than Gradient-based methods, Hebbian learning can perform online learning, which suggests that this combined strategy might be useful to design Online Machine Learning Algorithms for Image Classification.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Hebbian Learning optimizes specific functions, see [9].
- 2.
Links of the videos and full code can be found in https://github.com/Pherjev/Hebbian-CNN.
References
Aguilar Canto, F.J.: Eficacia de diferentes reglas hebbianas en el aprendizaje supervisado. Tecnología Educativa Revista CONAIC 7(1), 92–97 (2020)
Amato, G., Carrara, F., Falchi, F., Gennaro, C., Lagani, G.: Hebbian learning meets deep convolutional neural networks. In: Ricci, E., Rota Bulò, S., Snoek, C., Lanz, O., Messelodi, S., Sebe, N. (eds.) ICIAP 2019. LNCS, vol. 11751, pp. 324–334. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30642-7_29
Bahroun, Y., Hunsicker, E., Soltoggio, A.: Building efficient deep Hebbian networks for image classification tasks. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10613, pp. 364–372. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68600-4_42
Bahroun, Y., Soltoggio, A.: Online representation learning with single and multi-layer Hebbian networks for image classification. In: Lintas, A., Rovetta, S., Verschure, P.F.M.J., Villa, A.E.P. (eds.) ICANN 2017. LNCS, vol. 10613, pp. 354–363. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-68600-4_41
Baldominos, A., Saez, Y., Isasi, P.: A survey of handwritten character recognition with MNIST and EMNIST. Appl. Sci. 9(15), 3169 (2019)
Bienenstock, E.L., Cooper, L.N., Munro, P.W.: Theory for the development of neuron selectivity: orientation specificity and binocular interaction in visual cortex. J. Neurosci. 2(1), 32–48 (1982)
Bliss, T.V., Cooke, S.F.: Long-term potentiation and long-term depression: a clinical perspective. Clinics 66, 3–17 (2011)
Bromer, C., et al.: Long-term potentiation expands information content of hippocampal dentate gyrus synapses. Proc. Natl. Acad. Sci. 115(10), E2410–E2418 (2018)
Choe, Y.: Hebbian Learning. Springer, Incorporated (2015)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp. 1251–1258 (2017)
Cohen, G., Afshar, S., Tapson, J., Van Schaik, A.: EMNIST: extending MNIST to handwritten letters. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2921–2926. IEEE (2017)
Cooper, L.N., Bear, M.F.: The BCM theory of synapse modification at 30: interaction of theory with experiment. Nat. Rev. Neurosci. 13(11), 798–810 (2012)
Dayan, P., Abbott, L.: Computational neuroscience (2002)
Dorfer, M., Kelz, R., Widmer, G.: Deep linear discriminant analysis. arXiv preprint arXiv:1511.04707 (2015)
Elson, J., Douceur, J.J., Howell, J., Saul, J.: Asirra: a CAPTCHA that exploits interest-aligned manual image categorization. In: Proceedings of 14th ACM Conference on Computer and Communications Security (CCS). Association for Computing Machinery, Inc., October 2007
Erhan, D., Bengio, Y., Courville, A., Vincent, P.: Visualizing higher-layer features of a deep network. Univ. Montreal 1341(3), 1 (2009)
Hahnloser, R.H., Sarpeshkar, R., Mahowald, M.A., Douglas, R.J., Seung, H.S.: Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature 405(6789), 947–951 (2000)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)
Hebb, D.O.: The Organization of Behavior: A Neuropsychological Theory. Wiley, Chapman & Hall, New York (1949)
Holca-Lamarre, R., Lücke, J., Obermayer, K.: Models of acetylcholine and dopamine signals differentially improve neural representations. Front. Comput. Neurosci. 11, 54 (2017)
Hubel, D.H., Wiesel, T.N.: Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex. J. Physiol. 160(1), 106 (1962)
Keck, C., Savin, C., Lücke, J.: Feedforward inhibition and synaptic scaling-two sides of the same coin? PLoS Comput. Biol. 8(3), e1002432 (2012)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, pp. 1097–1105 (2012)
Kuśmierz, Ł., Isomura, T., Toyoizumi, T.: Learning with three factors: modulating Hebbian plasticity with errors. Curr. Opin. Neurobiol. 46, 170–177 (2017)
Kussul, E., Baidyk, T., Kasatkina, L., Lukovich, V.: Rosenblatt perceptrons for handwritten digit recognition. In: International Joint Conference on Neural Networks. Proceedings (Cat. No. 01CH37222), IJCNN 2001, vol. 2, pp. 1516–1520. IEEE (2001)
Law, C.C., Cooper, L.N.: Formation of receptive fields in realistic visual environments according to the Bienenstock, Cooper, and Munro (BCM) theory. Proc. Natl. Acad. Sci. 91(16), 7797–7801 (1994)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
LeCun, Y., Cortes, C., Burges, C.: Mnist handwritten digit database (2010) http://yann.lecun.com/exdb/mnist 7, 23 (2010)
Li, G., Liu, M., Dong, M.: A new online learning algorithm for structure-adjustable extreme learning machine. Comput. Math. Appl. 60(3), 377–389 (2010)
Liu, D., Yue, S.: Visual pattern recognition using unsupervised spike timing dependent plasticity learning. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 285–292. IEEE (2016)
Lomo, T.: Frequency potentiation of excitatory synaptic activity in dentate area of hippocampal formation. In: Acta Physiologica Scandinavica. p. 128. BLACKWELL SCIENCE LTD PO BOX 88, OSNEY MEAD, OXFORD OX2 0NE, OXON, ENGLAND (1966)
Lüscher, C., Malenka, R.C.: NMDA receptor-dependent long-term potentiation and long-term depression (LTP/LTD). Cold Spring Harb. Perspect. Biol. 4(6), a005710 (2012)
Magotra, A., kim, J.: Transfer learning for image classification using Hebbian plasticity principles. In: Proceedings of the 2019 3rd International Conference on Computer Science and Artificial Intelligence, pp. 233–238 (2019)
Mannor, S., Peleg, D., Rubinstein, R.: The cross entropy method for classification. In: Proceedings of the 22nd international conference on Machine Learning, pp. 561–568 (2005)
Nicoll, R.A.: A brief history of long-term potentiation. Neuron 93(2), 281–290 (2017)
Nocedal, J., Wright, S.: Numerical Optimization. Springer, Heidelberg (2006)
Oja, E.: Simplified neuron model as a principal component analyzer. J. Math. Biol. 15(3), 267–273 (1982)
Palacios-Filardo, J., Mellor, J.R.: Neuromodulation of hippocampal long-term synaptic plasticity. Curr. Opin. Neurobiol. 54, 37–43 (2019)
Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386 (1958)
Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211–252 (2015)
Sahoo, D., Pham, Q., Lu, J., Hoi, S.C.: Online deep learning: learning deep neural networks on the fly. arXiv preprint arXiv:1711.03705 (2017)
Seeliger, K., et al.: Convolutional neural network-based encoding and decoding of visual object recognition in space and time. NeuroImage 180, 253–266 (2018)
Sejnowski, T.J., Tesauro, G.: Building network learning algorithms from Hebbian synapses. In: Brain Organization and Memory: Cells, Systems, and Circuits, pp. 338–355. Oxford University Press, New York (1989)
Serre, T.: Hierarchical Models of the Visual System. Springer Publishing Company, Incorporated (2015)
Shim, H.G., et al.: Long-term depression of intrinsic excitability accompanied by synaptic depression in cerebellar Purkinje cells. J. Neurosci. 37(23), 5659–5669 (2017)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Szegedy, C., Ioffe, S., Vanhoucke, V., Alemi, A.A.: Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)
Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2818–2826 (2016)
Wadhwa, A., Madhow, U.: Bottom-up deep learning using the Hebbian principle (2016)
Acknowledgments
I would like to thank Carlos Francisco Brito-Loeza for his comments and support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Aguilar Canto, F.J. (2020). Convolutional Neural Networks with Hebbian-Based Rules in Online Transfer Learning. In: Martínez-Villaseñor, L., Herrera-Alcántara, O., Ponce, H., Castro-Espinoza, F.A. (eds) Advances in Soft Computing. MICAI 2020. Lecture Notes in Computer Science(), vol 12468. Springer, Cham. https://doi.org/10.1007/978-3-030-60884-2_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-60884-2_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-60883-5
Online ISBN: 978-3-030-60884-2
eBook Packages: Computer ScienceComputer Science (R0)