Abstract
Both synaptic plasticity rules (the so-called Hebbian rules) and Convolutional Neural Networks are based on or inspired by well-established models of Computational Neuroscience about mammal vision. There are some theoretical advantages associated with these frameworks, including online learning in Hebbian Learning. In the case of Convolutional Neural Networks, such advantages have been translated into remarkable results in image classification in the last decade. Nevertheless, such success is not shared in Hebbian Learning. In this paper, we explore the hypothesis of the necessity of a wider dataset for the classification of mono-instantiated objects, this is, objects that can be represented in a single cluster in the feature space. By using 15 mono-instantiated classes, the Adam optimizer reaches the maximum accuracy with fewer examples but using more epochs. In comparison, Hebbian rule BCM demands more examples but keeps using real-time learning. This result is a positive answer to the principal hypothesis and enlights how Hebbian learning can find a niche in the mainstream of Deep Learning.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Aguilar Canto, F., Brito-Loeza, C.: El potencial del aprendizaje hebbiano en la clasificación supervisada. Boletín de la Sociedad Mexicana de Computación Científica y sus Aplicaciones (2021)
Aguilar-Canto, F., Calvo, H.: A hebbian approach to non-spatial prelinguistic reasoning. Brain Sci. 12(2), 281 (2022)
Aguilar Canto, F.J.: 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.) MICAI 2020. LNCS (LNAI), vol. 12468, pp. 35–49. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-60884-2_3
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
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., Lømo, T.: Long-lasting potentiation of synaptic transmission in the dentate area of the anaesthetized rabbit following stimulation of the perforant path. J. Physiol. 232(2), 331–356 (1973)
Burbank, K.S.: Mirrored STDP implements autoencoder learning in a network of spiking neurons. PLoS Comput. Biol. 11(12), e1004566 (2015)
Cao, Y., Chen, Y., Khosla, D.: Spiking deep convolutional neural networks for energy-efficient object recognition. Int. J. Comput. Vision 113(1), 54–66 (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)
Dayan, P., Abbott, L.F.: Theoretical neuroscience: computational and mathematical modeling of neural systems (2001)
Desimone, R., Albright, T.D., Gross, C.G., Bruce, C.: Stimulus-selective properties of inferior temporal neurons in the macaque. J. Neurosci. 4(8), 2051–2062 (1984)
Fukushima, K.: Neocognitron: a hierarchical neural network capable of visual pattern recognition. Neural Netw. 1(2), 119–130 (1988)
Han, K., et al.: A survey on vision transformer. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2022)
He, K., Zhang, X., Ren, S., and Sun, J.: Delving deep into rectifiers: Surpassing human-level performance on imageNet classification. In: Proceedings of the IEEE international conference on computer vision, pp. 1026–1034 (2015)
Herzog, M.H., Clarke, A.M.: Why vision is not both hierarchical and feedforward. Front. Comput. Neurosci. 8, 135 (2014)
Holca-Lamarre, R., Lücke, J., Obermayer, K.: Models of acetylcholine and dopamine signals differentially improve neural representations. Front. Comput. Neurosci. 11, 54 (2017)
Huang, Y., Liu, J., Harkin, J., McDaid, L., Luo, Y.: An memristor-based synapse implementation using BCM learning rule. Neurocomputing 423, 336–342 (2021)
Keck, C., Savin, C., Lücke, J.: Feedforward inhibition and synaptic scaling-two sides of the same coin? PLoS Comput. Biol. 8(3), e1002432 (2012)
Kheradpisheh, S.R., Ganjtabesh, M., Masquelier, T.: Bio-inspired unsupervised learning of visual features leads to robust invariant object recognition. Neurocomputing 205, 382–392 (2016)
Kheradpisheh, S.R., Ganjtabesh, M., Thorpe, S.J., Masquelier, T.: STDP-based spiking deep convolutional neural networks for object recognition. Neural Netw. 99, 56–67 (2018)
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In 3rd International Conference for Learning Representations, San Diego (2015)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems 25 (2012)
Lagani, G., Falchi, F., Gennaro, C., Amato, G.: Evaluating hebbian learning in a semi-supervised setting. In: LOD 2021. LNCS, vol. 13164, pp. 365–379. Springer, cham (2021). https://doi.org/10.1007/978-3-030-95470-3_28
Lagani, G., Falchi, F., Gennaro, C., Amato, G.: Hebbian semi-supervised learning in a sample efficiency setting. Neural Netw. 143, 719–731 (2021)
Lagani, G., Falchi, F., Gennaro, C., Amato, G.: Training convolutional neural networks with competitive hebbian learning approaches. In: LOD 2021. LNCS, vol. 13163, pp. 25–40. Springer, cham (2021). https://doi.org/10.1007/978-3-030-95467-3_2
Lagani, G., Falchi, F., Gennaro, C., Amato, G.: Comparing the performance of hebbian against backpropagation learning using convolutional neural networks. In: Neural Computing and Applications, pp. 1–17 (2022)
LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278–2324 (1998)
Lillicrap, T.P., Santoro, A., Marris, L., Akerman, C.J., Hinton, G.: Backpropagation and the brain. Nat. Rev. Neurosci. 21(6), 335–346 (2020)
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)
Lømo, 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)
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)
Magotra, A., Kim, J.: Improvement of heterogeneous transfer learning efficiency by using hebbian learning principle. Appl. Sci. 10(16), 5631 (2020)
Magotra, A., Kim, J.: Neuromodulated dopamine plastic networks for heterogeneous transfer learning with hebbian principle. Symmetry 13(8), 1344 (2021)
Markram, H., Lübke, J., Frotscher, M., Sakmann, B.: Regulation of synaptic efficacy by coincidence of postsynaptic aps and EPSPs. Science 275(5297), 213–215 (1997)
Masquelier, T., Thorpe, S.J.: Unsupervised learning of visual features through spike timing dependent plasticity. PLoS Comput. Biol. 3(2), e31 (2007)
McMahan, H.B., et al.: Ad click prediction: a view from the trenches. In: Proceedings of the 19th ACM SIGKDD international conference on Knowledge discovery and data mining, pp. 1222–1230 (2013)
Miconi, T.: Hebbian learning with gradientes: hebbian convolutional neural networks with modern deep learning frameworks. arXiv preprint arXiv:2107.01729
Miconi, T., Rawal, A., Clune, J., Stanley, K.O.: Backpropamine: training self-modifying neural networks with differentiable neuromodulated plasticity. arXiv preprint arXiv:2002.10585
Miconi, T., Stanley, K., Clune, J.: Differentiable plasticity: training plastic neural networks with backpropagation. In: International Conference on Machine Learning, pp. 3559–3568. PMLR (2018)
Oja, E.: A simplified neuron model as a principal component analyzer. J. Math. Biol. 15(3), 267–273 (1982)
Panda, P., Roy, K.: Unsupervised regenerative learning of hierarchical features in spiking deep networks for object recognition. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 299–306. IEEE (2016)
Pogodin, R., Mehta, Y., Lillicrap, T., Latham, P.: Towards biologically plausible convolutional networks. In: Advances in Neural Information Processing Systems 34 (2021)
Riesenhuber, M., Poggio, T.: Hierarchical models of object recognition in cortex. Nat. Neurosci. 2(11), 1019–1025 (1999)
Rolls, E.: Neurons in the cortex of the temporal lobe and in the amygdala of the monkey with responses selective for faces. Hum. Neurobiol. 3(4), 209–222 (1984)
Rosenblatt, F.: The perceptron: a probabilistic model for information storage and organization in the brain. Psychol. Rev. 65(6), 386 (1958)
Tavanaei, A., Ghodrati, M., Kheradpisheh, S.R., Masquelier, T., Maida, A.: Deep learning in spiking neural networks. Neural Netw. 111, 47–63 (2019)
Tavanaei, A., Masquelier, T., Maida, A.: Representation learning using event-based STDP. Neural Netw. 105, 294–303 (2018)
Tavanaei, A., Masquelier, T., Maida, A.S.: Acquisition of visual features through probabilistic spike-timing-dependent plasticity. In: 2016 International Joint Conference on Neural Networks (IJCNN), pp. 307–314. IEEE (2016)
Van Essen, D.C., Maunsell, J.H.: Hierarchical organization and functional streams in the visual cortex. Trends Neurosci. 6, 370–375 (1983)
Wadhwa, A., Madhow, U.: Bottom-up deep learning using the hebbian principle (2016)
Wallis, G.: Using spatio-temporal correlations to learn invariant object recognition. Neural Netw. 9(9), 1513–1519 (1996)
Yeo, W.-H., Heo, Y.-J., Choi, Y.-J., Kim, B.-G.: Place classification algorithm based on semantic segmented objects. Appl. Sci. 10(24), 9069 (2020)
Zhao, B., Ding, R., Chen, S., Linares-Barranco, B., Tang, H.: Feedforward categorization on AER motion events using cortex-like features in a spiking neural network. IEEE Trans. Neural Netw. Learn. Syst. 26(9), 1963–1978 (2014)
Hubel, D.H., Wiesel, T.N.: Receptive fields of single neurones in the cat’s striate cortex. J. Physiol. 148(3), 574 (1959). Wiley-Blackwell
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). Wiley-Blackwell
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Aguilar-Canto, F., Calvo, H. (2022). The Role of the Number of Examples in Convolutional Neural Networks with Hebbian Learning. In: Pichardo Lagunas, O., Martínez-Miranda, J., Martínez Seis, B. (eds) Advances in Computational Intelligence. MICAI 2022. Lecture Notes in Computer Science(), vol 13612. Springer, Cham. https://doi.org/10.1007/978-3-031-19493-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-031-19493-1_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-19492-4
Online ISBN: 978-3-031-19493-1
eBook Packages: Computer ScienceComputer Science (R0)