Affiliation:
1. Department of Computer-Aided Design, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, Russia
2. Youth Research Institute, St. Petersburg Electrotechnical University “LETI”, 5 Professora Popova St., 197022 Saint Petersburg, Russia
Abstract
For the last two decades, artificial neural networks (ANNs) of the third generation, also known as spiking neural networks (SNN), have remained a subject of interest for researchers. A significant difficulty for the practical application of SNNs is their poor suitability for von Neumann computer architecture, so many researchers are currently focusing on the development of alternative hardware. Nevertheless, today several experimental libraries implementing SNNs for conventional computers are available. In this paper, using the RCNet library, we compare the performance of reservoir computing architectures based on artificial and spiking neural networks. We explicitly show that, despite the higher execution time, SNNs can demonstrate outstanding classification accuracy in the case of complicated datasets, such as data from industrial sensors used for the fault detection of bearings and gears. For one of the test problems, namely, ball bearing diagnosis using an accelerometer, the accuracy of the classification using reservoir SNN almost reached 100%, while the reservoir ANN was able to achieve recognition accuracy up to only 61%. The results of the study clearly demonstrate the superiority and benefits of SNN classificators.
Funder
Russian Science Foundation
Subject
Artificial Intelligence,Computer Science Applications,Information Systems,Management Information Systems
Reference32 articles.
1. Deep learning in spiking neural networks;Tavanaei;Neural Networks,2019
2. Comparison of artificial and spiking neural networks on digital hardware;Davidson;Front. Neurosci.,2021
3. Przyczyna, D., Pecqueur, S., Vuillaume, D., and Szaciłowski, K. (2020). Reservoir computing for sensing: An experimental approach. arXiv.
4. Activation functions in neural networks;Sharma;Towards Data Sci.,2017
5. Training multi-layer spiking neural networks using NormAD based spatio-temporal error backpropagation;Anwani;Neurocomputing,2020
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献