The bioinspired traffic sign classifier

• Autorzy: Przewlocka-Rus Dominika , Kryjak Tomasz

Identyfikatory

DOI

10.1515/bams-2021-0159

• Języki publikacji: EN

Abstrakty

EN

Objectives: In this paper the research on developing convolutional spiking neural networks for traffic signs classification is presented. Unlike classical ones, spiking networks reflect the behaviour of biological neurons much more closely, by taking into account the time dimension and event-based operation. Spiking networks running on dedicated neuromorphic platforms, such as Intel Loihi, can operate with greater energy efficiency, hence they are an interesting approach for embedded solutions. Methods: For convolutional spiking neural networks' design and simulation, Nengo and NengoDL libraries for Python language were used. Numerous experiments using the Leaky-Integrate-and-Fire (LIF) neuron model were conducted. The training results, with different augmentation methods and number of time steps for input image presentation were compared. Results: Finally, an accuracy of up to 97% on the test set was achieved, depending on the number of time steps the input was presented to the SNN. Conclusions: The proposed experiments show that using simple convolutional spiking neural network, one can achieve accuracy comparable to the classical network with the same architecture and trained on the same dataset. At the same time, running on dedicated neuromorphic hardware, such solution should be characterized by low latency and low energy consumption.

Słowa kluczowe

EN

neuromorphic computing; spiking neural networks; traffic sign classifier

• Wydawca: Uniwersytet Jagielloński - Collegium Medicum ; Index Copernicus Sp. z o.o.
• Czasopismo: Bio-Algorithms and Med-Systems
• Rocznik: 2022
• Tom: Vol. 18, no. 1
• Strony: 29--38
• Opis fizyczny: Bibliogr. 17 poz., rys., tab.

Twórcy

autor

Przewlocka-Rus Dominika

• AGH University of Science and Technology, Krakow, Poland

• https://orcid.org/0000-0002-5836-8604

autor

Kryjak Tomasz

• AGH University of Science and Technology, Krakow, Poland

• https://orcid.org/0000-0001-6798-4444

Bibliografia

• 1. Paugam-Moisy H, Bohte S. Computing with Spiking Neuron Networks. In: Handbook of Natural Computing. Springer-Verlag; 2012:335-76 pp.
• 2. Hunsberger E, Eliasmith C. Training Spiking Deep Networks for Neuromorphic Hardware. CoRR. abs/1611.05141; 2016.
• 3. O’Connor P, Welling M. Deep Spiking Networks. CoRR. abs/1602.08323; 2016.
• 4. Lee J, Delbruck T, Pfeiffer M. Training Deep Spiking Neural Networks Using Backpropagation. Front Neurosci 2016;10:508.
• 5. Diehl P, Neil D, Binas J, Cook M, Liu S, Pfeiffer M. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In: 2015 International Joint Conference On Neural Networks (IJCNN); 2015:1-8 pp.
• 6. Ranjan J, Sigamani T, Barnabas J. A novel and efficient classifier using spiking neural network. J Supercomput 2020;76:6545-60.
• 7. Rasmussen D. NengoDL: combining deep learning and neuromorphic modelling methods. CoRR. abs/18052018.11144.
• 8. Stallkamp J, Schlipsing M, Salmen J, Igel C. The German Traffic Sign Recognition Benchmark: a multi-class classification competition. In: IEEE International Joint Conference On Neural Networks; 2011:1453-60 pp.
• 9. Cireşan D, Meier U, Masci J, Schmidhuber J. Multi-column deep neural network for traffic sign classification. Neural Networks 2012;32:333-8.
• 10. Sermanet P, LeCun Y. Traffic sign recognition with multi-scale Convolutional Networks. In: The 2011 International Joint Conference On Neural Networks; 2011:2809-13 pp.
• 11. Zaklouta F, Stanciulescu B, Hamdoun O. Traffic sign classification using K-d trees and Random Forests. In: The 2011 International Joint Conference On Neural Networks; 2011:2151-5 pp.
• 12. Arcos-García Á, Á lvarez-García J, Soria-Morillo L. Deep neural network for traffic sign recognition systems: An analysis of spatial transformers and stochastic optimisation methods. Neural Networks 2018;99:158-65.
• 13. Zuiderveld K. Contrast Limited Adaptive Histogram Equalization. In: Graphics Gems. Academic Press; 1994:474-85 pp.
• 14. Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE 1998;86:2278-324.
• 15. Springenberg J, Dosovitskiy A, Brox T, Riedmiller M. Striving for Simplicity: The All Convolutional Net. CoRR; 2015.
• 16. Intel. Lava Tool. https://github.com/lava-nc/lava.
• 17. Kim S, Park S, Na B, Yoon S. Spiking-YOLO: Spiking Neural Network for Real-time Object Detection. CoRR. abs/1903.06530; 2019.

Uwagi

Opublikowane przez De Gruyter. Opracowanie rekordu ze środków MEiN, umowa nr SONP/SP/546092/2022 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2022-2023).