Impact of Noisy Input on Evolved Spiking Neural Networks for Neuromorphic Systems

被引:3
作者
Patel, Karan P. [1 ]
Schuman, Catherine D. [1 ]
机构
[1] Univ Tennessee, Dept EECS, Knoxville, TN 37996 USA
来源
PROCEEDINGS OF THE 2023 ANNUAL NEURO-INSPIRED COMPUTATIONAL ELEMENTS CONFERENCE, NICE 2023 | 2023年
关键词
neuromorphic computing; spiking neural networks; evolutionary algorithms;
D O I
10.1145/3584954.3584969
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In this work we leverage a simple spiking neuromorphic processor and an evolutionary-based training method to train and test networks in classification and control applications with noise injection in order to explore the resilience and robustness of spiking neural networks on neuromorphic systems. Through our implementation, we were able to observe that injecting noise within the training phase produces more robust networks that are more resilient to noise within the testing phase. Compared to the performance of other popular classifiers on simple data classification tasks, SNNs perform behind nearest neighbors and linear SVM, and above decision trees and traditional neural networks, with respect to performance in the presence of input noise.
引用
收藏
页码:52 / 56
页数:5
相关论文
共 17 条
[1]  
BanaGozar A, 2017, DES AUT TEST EUROPE, P440, DOI 10.23919/DATE.2017.7927030
[2]  
Brockman G, 2016, Arxiv, DOI arXiv:1606.01540
[3]   Supervised training of spiking neural networks for robust deployment on mixed-signal neuromorphic processors [J].
Buechel, Julian ;
Zendrikov, Dmitrii ;
Solinas, Sergio ;
Indiveri, Giacomo ;
Muir, Dylan R. .
SCIENTIFIC REPORTS, 2021, 11 (01)
[4]  
Schuman CD, 2017, Arxiv, DOI arXiv:1705.06963
[5]  
Dimovska M, 2019, 2019 IEEE 10TH ANNUAL UBIQUITOUS COMPUTING, ELECTRONICS & MOBILE COMMUNICATION CONFERENCE (UEMCON), P433, DOI [10.1109/uemcon47517.2019.8992983, 10.1109/UEMCON47517.2019.8992983]
[6]   Neural Coding in Spiking Neural Networks: A Comparative Study for Robust Neuromorphic Systems [J].
Guo, Wenzhe ;
Fouda, Mohammed E. ;
Eltawil, Ahmed M. ;
Salama, Khaled Nabil .
FRONTIERS IN NEUROSCIENCE, 2021, 15
[7]   Rapid online learning and robust recall in a neuromorphic olfactory circuit [J].
Imam, Nabil ;
Cleland, Thomas A. .
NATURE MACHINE INTELLIGENCE, 2020, 2 (03) :181-191
[8]   RATE CODING OR DIRECT CODING: WHICH ONE IS BETTER FOR ACCURATE, ROBUST, AND ENERGY-EFFICIENT SPIKING NEURAL NETWORKS? [J].
Kim, Youngeun ;
Park, Hyoungseob ;
Moitra, Abhishek ;
Bhattacharjee, Abhiroop ;
Venkatesha, Yeshwanth ;
Panda, Priyadarshini .
2022 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2022, :71-75
[9]  
Li Yangyang, 2022, ASCL
[10]  
Marchisio A., 2021, 2021 INT JOINT C NEU, P1