Optimizing Binary Neural Network for Resource-Constrained Edge Devices in IoT Applications
Email tác giả liên hệ:
huanvm@hcmute.edu.vnDOI:
https://doi.org/10.54644/jte.2025.1756Từ khóa:
Binary Neural Network, XNOR-popcout, Edge device, IoT, Resource-constrained hardwareTóm tắt
The implementation of artificial intelligence models on edge devices is increasingly popular, bringing many values in reducing latency, effectively utilizing bandwidth, improving data security, enhancing privacy and reducing costs for users. However, this work poses many challenges in terms of accuracy, processing speed, hardware resources and model size for devices constrained by limited hardware. Binary Neural Network (BNN) is proposed as a potential solution to reduce resource requirements by using only 1 bit for quantizing. In this study, BNN network is optimized by binary quantizing both weights and activation functions with XNOR-popcout multiplication to optimize BNN network. The results show that BNN network model is lighter in memory footprint when deployed on hardware with limited computational resources, less computational time than conventional BNN network which helps the model execute faster as the network architecture becomes less complex, with acceptable accuracy on two datasets MNIST and Fashion MNIST. The proposed BNN model resul can be deployed on edge devices for IoT applications.
Tải xuống: 0
Tài liệu tham khảo
W. X. Zhao et al., “A survey of large language models,” arXiv preprint arXiv:2303.18223, 2023.
X. Zhang et al., “Adaptive precision training: Quantify back propagation in neural networks with fixed-point numbers,” arXiv preprint arXiv:1911.00361, 2019.
S. N. Truong, “A low-cost artificial neural network model for Raspberry Pi,” Eng. Technol. Appl. Sci. Res., vol. 10, 2020. DOI: https://doi.org/10.48084/etasr.3357
S. N. Truong, “A ternary neural network with compressed quantized weight matrix for low power embedded systems,” Eng. Technol. Appl. Sci. Res., vol. 12, pp. 8311–8315, 2022. DOI: https://doi.org/10.48084/etasr.4758
V. Mehlin, S. Schacht, and C. Lanquillon, “Towards energy-efficient deep learning: An overview of energy-efficient approaches along the deep learning lifecycle,” arXiv preprint arXiv:2303.01980, 2023.
Y. Li, W. Ding, C. Liu, B. Zhang, and G. Guo, “TRQ: Ternary neural networks with residual quantization,” Proc. AAAI Conf. Artif. Intell., vol. 35, no. 10, pp. 8538–8546, May 2021. DOI: https://doi.org/10.1609/aaai.v35i10.17036
I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, “Binarized neural networks,” Adv. Neural Inf. Process. Syst., vol. 29, 2016.
I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, “Quantized neural networks: Training neural networks with low precision weights and activations,” J. Mach. Learn. Res., vol. 18, pp. 1–30, 2018.
M. Rastegari, V. Ordonez, J. Redmon, and A. Farhadi, “XNOR-Net: ImageNet classification using binary convolutional neural networks,” in Proc. Eur. Conf. Comput. Vis. (ECCV), 2016, pp. 525–542. DOI: https://doi.org/10.1007/978-3-319-46493-0_32
Y. Guo, “A survey on methods and theories of quantized neural networks,” arXiv preprint arXiv:1808.04752, 2018.
X. Yao, “A review of evolutionary artificial neural networks,” Int. J. Intell. Syst., vol. 8, pp. 539–567, 1993. DOI: https://doi.org/10.1002/int.4550080406
I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016.
Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, pp. 2278–2324, 1998. DOI: https://doi.org/10.1109/5.726791
W. Rawat and Z. Wang, “Deep convolutional neural networks for image classification: A comprehensive review,” Neural Comput., vol. 29, pp. 2352–2449, 2017. DOI: https://doi.org/10.1162/neco_a_00990
S. Agrawal, V. Rewaskar, R. Agrawal, S. Chaudhari, Y. Patil, and N. Agrawal, “Advancements in NSFW content detection: A comprehensive review of ResNet-50 based approaches,” Int. J. Intell. Syst. Appl. Eng., vol. 11, pp. 41–45, 2023.
M. Courbariaux, I. Hubara, D. Soudry, R. El-Yaniv, and Y. Bengio, “Binarized neural networks: Training deep neural networks with weights and activations constrained to +1 or −1,” arXiv preprint arXiv:1602.02830, 2016.
T. Ma, Z. Li, Q. Li, H. Liu, Z. Zhao, and Y. Wang, “FPGA optimized architecture of XNOR-POPCOUNT,” in Proc. Int. Conf. Comput., Commun., Percept. Quantum Technol. (CCPQT), Xiamen, China, 2023, pp. 235–239, doi: 10.1109/CCPQT60491.2023.00046. DOI: https://doi.org/10.1109/CCPQT60491.2023.00046
P. V. Khoa, T. N. Quang, and N. N. Lam, “Optimizing the convolutional neural networks for resource-constraint hardwares,” J. Intell. Syst. Appl. Eng., vol. 5, no. 1, pp. 1332–1341, 2022.
C. Yuan and S. S. Agaian, “A comprehensive review of binary neural network,” Artif. Intell. Rev., vol. 56, pp. 12949–13013, 2023. DOI: https://doi.org/10.1007/s10462-023-10464-w
Tải xuống
Đã Xuất bản
Cách trích dẫn
Số
Chuyên mục
Categories
Giấy phép
Bản quyền (c) 2025 Tạp chí Khoa học Giáo dục Kỹ Thuật
Tác phẩm này được cấp phép theo Giấy phép quốc tế Creative Commons Attribution-NonCommercial 4.0 .
Bản quyền thuộc về JTE.
