Abstract
In event-based vision, visual information is encoded by sequential events in space and time, similar to the human visual system, where the retina emits spikes. Thus, spiking neural networks are to be preferred for processing event-based input streams. As for classical deep learning networks, spiking neural networks must be robust against different corruption or perturbations in the input data. However, corruption in event-based data has received little attention so far. According to previous studies, biologically motivated neural networks, consisting of lateral inhibition to implement a competition mechanism between the neurons, show an increase in the robustness against loss of information of input data. We here analyze the influence of inhibitory feedback on the robustness against four different types of corruption on an event-based data set. We demonstrate how a 1 : 1 ratio between feed-forward excitation and feedback inhibition increases the robustness against the loss of events, as well as against additional noisy events. Interestingly, our results show that strong feedback inhibition is a disadvantage if events in the input stream are shifted in space or in time.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Akhtar, N., Mian, A., Kardan, N., Shah, M.: Advances in adversarial attacks and defenses in computer vision: a survey. IEEE Access 9, 155161–155196 (2021). https://doi.org/10.1109/ACCESS.2021.3127960
Büchel, J., Lenz, G., Hu, Y., Sheik, S., Sorbaro, M.: Adversarial attacks on spiking convolutional neural networks for event-based vision. Front. Neurosci. 16 (2022). https://doi.org/10.3389/fnins.2022.1068193
Clopath, C., Büsing, L., Vasilaki, E., Gerstner, W.: Connectivity reflects coding: a model of voltage-based STDP with homeostasis. Nat. Neurosci. 13(3), 344–352 (2010). https://doi.org/10.1038/nn.2479
Gallego, G., et al.: Event-based vision: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44(01), 154–180 (2022). https://doi.org/10.1109/TPAMI.2020.3008413
Gilbert, C.D., Li, W.: Top-down influences on visual processing. Nat. Rev. Neurosci. 14(5), 350–363 (2013). https://doi.org/10.1038/nrn3476
Hendrycks, D., Dietterich, T.: Benchmarking neural network robustness to common corruptions and perturbations. In: Proceedings of the International Conference on Learning Representations (2019)
Iyer, L.R., Basu, A.: Unsupervised learning of event-based image recordings using spike-timing-dependent plasticity. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 1840–1846 (2017). https://doi.org/10.1109/IJCNN.2017.7966074
Kermani Kolankeh, A., Teichmann, M., Hamker, F.H.: Competition improves robustness against loss of information. Front. Comput. Neurosci. 9 (2015). https://doi.org/10.3389/fncom.2015.00035
Kim, E., Rego, J., Watkins, Y., Kenyon, G.T.: Modeling biological immunity to adversarial examples. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4665–4674 (2020). https://doi.org/10.1109/CVPR42600.2020.00472
Larisch, R., Teichmann, M., Hamker, F.H.: A neural spiking approach compared to deep feedforward networks on stepwise pixel erasement. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11139, pp. 253–262. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01418-6_25
Larisch, R., Gönner, L., Teichmann, M., Hamker, F.H.: Sensory coding and contrast invariance emerge from the control of plastic inhibition over emergent selectivity. PLOS Comput. Biol. 17(11), 1–37 (2021). https://doi.org/10.1371/journal.pcbi.1009566
Lee, C., Sarwar, S.S., Panda, P., Srinivasan, G., Roy, K.: Enabling spike-based backpropagation for training deep neural network architectures. Front. Neurosci. 14 (2020). https://doi.org/10.3389/fnins.2020.00119
Lenz, G., et al.: Tonic: event-based datasets and transformations, July 2021. https://doi.org/10.5281/zenodo.5079802, Documentation available under https://tonic.readthedocs.io
Markram, H., Toledo-Rodriguez, M., Wang, Y., Gupta, A., Silberberg, G., Wu, C.: Interneurons of the neocortical inhibitory system. Nat. Rev. Neurosci. 5(10), 793–807 (2004). https://doi.org/10.1038/nrn1519
Miconi, T., McKinstry, J.L., Edelman, G.M.: Spontaneous emergence of fast attractor dynamics in a model of developing primary visual cortex. Nat. Commun. 7(1), 13208 (2016). https://doi.org/10.1038/ncomms13208
Naud, R., Marcille, N., Clopath, C., Gerstner, W.: Firing patterns in the adaptive exponential integrate-and-fire model. Biol. Cybern. 99(4), 335–347 (2008). https://doi.org/10.1007/s00422-008-0264-7
Nunes, J.D., Carvalho, M., Carneiro, D., Cardoso, J.S.: Spiking neural networks: a survey. IEEE Access 10, 60738–60764 (2022). https://doi.org/10.1109/ACCESS.2022.3179968
Orchard, G., Jayawant, A., Cohen, G.K., Thakor, N.: Converting static image datasets to spiking neuromorphic datasets using saccades. Front. Neurosci. 9, 437 (2015)
Patiño-Saucedo, A., Rostro-González, H., Serrano-Gotarredona, T., Linares-Barranco, B.: Event-driven implementation of deep spiking convolutional neural networks for supervised classification using the spinnaker neuromorphic platform. Neural Netw. 121, 319–328 (2020). https://doi.org/10.1016/j.neunet.2019.09.008
Patiño-Saucedo, A., Rostro-González, H., Serrano-Gotarredona, T., Linares-Barranco, B.: Liquid state machine on spinnaker for spatio-temporal classification tasks. Front. Neurosci. 16 (2022). https://doi.org/10.3389/fnins.2022.819063
Spoerer, C.J., McClure, P., Kriegeskorte, N.: Recurrent convolutional neural networks: a better model of biological object recognition. Front. Psychol. 8 (2017). https://doi.org/10.3389/fpsyg.2017.01551
Teichmann, M., Larisch, R., Hamker, F.H.: Performance of biologically grounded models of the early visual system on standard object recognition tasks. Neural Netw. 144, 210–228 (2021). https://doi.org/10.1016/j.neunet.2021.08.009
Vitay, J., Dinkelbach, H., Hamker, F.: ANNarchy: a code generation approach to neural simulations on parallel hardware. Front. Neuroinform. 9 (2015). https://doi.org/10.3389/fninf.2015.00019
Vogels, T.P., Sprekeler, H., Zenke, F., Clopath, C., Gerstner, W.: Inhibitory plasticity balances excitation and inhibition in sensory pathways and memory networks. Science 334(6062), 1569–1573 (2011). https://doi.org/10.1126/science.1211095
Zhang, H., Chen, H., Song, Z., Boning, D., Dhillon, I., Hsieh, C.J.: The limitations of adversarial training and the blind-spot attack. In: International Conference on Learning Representations (2019). https://openreview.net/forum?id=HylTBhA5tQ
Acknowledgements
This research has been funded by the Saxony State Ministry of Science and Art (SMWK3-7304/35/3-2021/4819) research initiative “Instant Teaming between Humans and Production Systems”
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Larisch, R., Berger, L., Hamker, F.H. (2023). Exploring the Role of Feedback Inhibition for the Robustness Against Corruptions on Event-Based Data. In: Iliadis, L., Papaleonidas, A., Angelov, P., Jayne, C. (eds) Artificial Neural Networks and Machine Learning – ICANN 2023. ICANN 2023. Lecture Notes in Computer Science, vol 14261. Springer, Cham. https://doi.org/10.1007/978-3-031-44198-1_17
Download citation
DOI: https://doi.org/10.1007/978-3-031-44198-1_17
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-44197-4
Online ISBN: 978-3-031-44198-1
eBook Packages: Computer ScienceComputer Science (R0)