AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Tsinghua Science and Technology Article
PDF (4.6 MB)
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript AI Chat Paper
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Open Access

GAAF: Searching Activation Functions for Binary Neural Networks Through Genetic Algorithm

Department of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
Pacific Northwest National Laboratory, Richland, WA 99354, USA
Show Author Information

Abstract

Binary neural networks (BNNs) show promising utilization in cost and power-restricted domains such as edge devices and mobile systems. This is due to its significantly less computation and storage demand, but at the cost of degraded performance. To close the accuracy gap, in this paper we propose to add a complementary activation function (AF) ahead of the sign based binarization, and rely on the genetic algorithm (GA) to automatically search for the ideal AFs. These AFs can help extract extra information from the input data in the forward pass, while allowing improved gradient approximation in the backward pass. Fifteen novel AFs are identified through our GA-based search, while most of them show improved performance (up to 2.54% on ImageNet) when testing on different datasets and network models. Interestingly, periodic functions are identified as a key component for most of the discovered AFs, which rarely exist in human designed AFs. Our method offers a novel approach for designing general and application-specific BNN architecture. GAAF will be released on GitHub.

Keywords

binary neural networks (BNNs)genetic algorithmactivation function

References

[1]
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.
Google Scholar
[2]
I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, Binarized neural networks, in Proc. 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, 2016, pp. 4114–4122.
Google Scholar
[3]
Fasfous N., Vemparala M. -R., Frickenstein A., Frickenstein L., and Stechele W., BinaryCop: Binary neural network-based COVID-19 face-mask wear and positioning predictor on edge devices, arXiv preprint arXiv: 2102.03456, 2021.
Google Scholar
[4]
G. Chen, H. Meng, Y. Liang, and K. Huang, GPU-accelerated real-time stereo estimation with binary neural network, IEEE Transactions on Parallel and Distributed Systems, vol. 31, no. 12, pp. 2896–2907, 2020.
Crossref Google Scholar
[5]
C. -H. Huang, An FPGA-based hardware/software design using binarized neural networks for agricultural applications: A case study, IEEE Access, vol. 9, pp. 26523–26531.
Crossref Google Scholar
[6]
Y. Ma, H. Xiong, Z. Hu, and L. Ma, Efficient super resolution using binarized neural network, in Proc. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Long Beach, CA, USA, 2019, pp. 694–703, 2019.
Crossref Google Scholar
[7]
C. Ma, Y. Guo, Y. Lei, and W. An, Binary volumetric convolutional neural networks for 3-D object recognition, IEEE Transactions on Instrumentation and Measurement, vol. 68, no. 1, pp. 38–48, 2018.
Crossref Google Scholar
[8]
A. Li, T. Geng, T. Wang, M. Herbordt, S. L. Song, and K. Barker, BSTC: A novel binarized-soft-tensor-core design for accelerating bitbased approximated neural nets, in Proc. International Conference for High Performance Computing, Networking, Storage and Analysis, Denver, CO, USA, 2019, pp. 1–30.
Crossref Google Scholar
[9]
A. Galloway, G. W. Taylor, and M. Moussa, Attacking binarized neural networks, arXiv preprint arXiv:1711.00449, 2018.
Google Scholar
[10]
Y. Hu, J. Zhai, D. Li, Y. Gong, Y. Zhu, W. Liu, L. Su, and J. Jin, BitFlow: Exploiting vector parallelism for binary neural networks on CPU, in Proc. 2018 IEEE International Parallel and Distributed Processing Symposium (IPDPS), Vancouver, Canada, 2018, pp. 244–253.
Crossref Google Scholar
[11]
A. Li and S. Su, Accelerating binarized neural networks via bit-tensor-cores in turing GPUs, IEEE Transactions on Parallel and Distributed Systems, vol. 32, no. 7, pp. 1878–1891, 2020.
Crossref Google Scholar
[12]
T. Geng, T. Wang, C. Wu, C. Yang, W. Wu, A. Li, and M. C. Herbordt, O3BNN: An out-of-order architecture for high-performance binarized neural network inference with fine-grained pruning, in Proc. ACM International Conference on Supercomputing, Phoenix, AZ, USA, 2019, pp. 461–472.
Crossref Google Scholar
[13]
T. Geng, T. Wang, C. Wu, C. Yang, S. L. Song, A. Li, and M. Herbordt, LP-BNN: Ultra-low-latency BNN inference with layer parallelism, in Proc. 2019 IEEE 30th International Conference on Application-specific Systems, Architectures and Processors (ASAP), New York, NY, USA, 2019, pp. 9–16.
Crossref Google Scholar
[14]
T. Geng, A. Li, T. Wang, C. Wu, Y. Li, R. Shi, W. Wu, and M. Herbordt, O3BNN-R: An out-of-order architecture for high-performance and regularized BNN inference, IEEE Transactions on Parallel and Distributed Systems, vol. 32, no. 1, pp. 199–213, 2020.
Crossref Google Scholar
[15]
A. G. Anderson and C. P. Berg, The high-dimensional geometry of binary neural networks, arXiv preprint arXiv: 1705.07199, 2017.
Google Scholar
[16]
J. Bethge, C. Bartz, H. Yang, Y. Chen, and C. Meinel, MeliusNet: An improved network architecture for binary neural networks, in Proc. 2021 IEEE/CVF Winter Conference on Applications of Computer Vision, Waikoloa, HI, USA, 2021, pp. 1438–1447.
Crossref Google Scholar
[17]
Y. Bengio, N. Leonard, and A. Courville, Estimating or propagating gradients through stochastic neurons for conditional computation, arXiv preprint arXiv: 1308.3432, 2013.
Google Scholar
[18]
Z. Liu, B. Wu, W. Luo, X. Yang, W. Liu, and K. -T. Cheng, Bi-real net: Enhancing the performance of 1-bit CNNs with improved representational capability and advanced training algorithm, in Proc. European Conference on Computer Vision (ECCV), Munich, Germany, 2018, pp. 747–763.
Crossref Google Scholar
[19]
S. Darabi, M. Belbahri, M. Courbariaux, and V. P. Nia, BNN+: Improved binary network training, arXiv preprint arXiv: 1812.11800, 2018.
Google Scholar
[20]
C. Liu, W. Ding, X. Xia, B. Zhang, J. Gu, J. Liu, R. Ji, and D. Doermann, Circulant binary convolutional networks: Enhancing the performance of 1-bit DCNNs with circulant back propagation, in Proc. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 2019, pp. 2686–2694.
Crossref Google Scholar
[21]
H. Qin, R. Gong, X. Liu, M. Shen, Z. Wei, F. Yu, and J. Song, Forward and backward information retention for accurate binary neural networks, in Proc. 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 2020, pp. 2250–2259.
Crossref Google Scholar
[22]
F. Lahoud, R. Achanta, P. Márquez-Neila, and S. Süsstrunk, Self-binarizing networks, arXiv preprint arXiv: 1902.00730, 2019.
Google Scholar
[23]
Z. Liu, Z. Shen, M. Savvides, and K. -T. Cheng, ReActNet: Towards precise binary neural network with generalized activation functions, in Proc. European Conference on Computer Vision, Glasgow, UK, 2020, pp. 143–159.
Crossref Google Scholar
[24]
P. Ramachandran, B. Zoph, and Q. V. Le, Searching for activation functions, arXiv preprint arXiv: 1710.05941, 2017.
Google Scholar
[25]
H. Liu, A. Brock, K. Simonyan, and Q. V. Le, Evolving normalization-activation layers, arXiv preprint arXiv: 2004.02967, 2020.
Google Scholar
[26]
H. Liu, K. Simonyan, and Y. Yang, DARTS: Differentiable architecture search, arXiv preprint arXiv: 1806.09055, 2018.
Google Scholar
[27]
S. Han, H. Mao, and W. J. Dally, Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding, arXiv preprint arXiv: 1510.00149, 2015.
Google Scholar
[28]
D. Blalock, J. J. G. Ortiz, J. Frankle, and J. Guttag, What is the state of neural network pruning? arXiv preprint arXiv: 2003.03033, 2020.
Google Scholar
[29]
S. Ioffe and C. Szegedy, Batch normalization: Accelerating deep network training by reducing internal covariate shift, in Proc. 32nd International Conference on Machine Learning, Lile, France, 2015, pp. 448–456.
Google Scholar
[30]
D. E. Goldberg and J. H. Holland, Genetic algorithms and machine learning, Machine Learning, vol. 3, pp. 95–99, 1988.
Crossref Google Scholar
[31]
S. Katoch, S. S. Chauhan, and V. Kumar, A review on genetic algorithm: Past, present, and future, Multimedia Tools and Applications, vol. 80, pp. 8091–8126, 2020.
Crossref Google Scholar
[32]
D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, arXiv preprint arXiv: 1412.6980, 2014.
Google Scholar
[33]
W. Tang, G. Hua, and L. Wang, How to train a compact binary neural network with high accuracy? in Proc. Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA, 2017, pp. 2625–2631.
Crossref Google Scholar
[34]
S. Zhou, Y. Wu, Z. Ni, X. Zhou, H. Wen, and Y. Zou, DoReFa-Net: Training low bitwidth convolutional neural networks with low bitwidth gradients, arXiv preprint arXiv: 1606.06160, 2016.
Google Scholar
[35]
X. Lin, C. Zhao, and W. Pan, Towards accurate binary convolutional neural network, in Proc. Advances in Neural Information Processing Systems, Long Beach, CA, USA, 2017, pp. 345–353.
Google Scholar
[36]
M. Ghasemzadeh, M. Samragh, and F. Koushanfar, ReBNet: Residual binarized neural network, in Proc. 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM), Boulder, CO, USA, 2018, pp. 57–64.
Crossref Google Scholar
[37]
J. Bethge, H. Yang, M. Bornstein, and C. Meinel, BinaryDenseNet: Developing an architecture for binary neural networks, in Proc. IEEE/CVF International Conference on Computer Vision Workshops, Seoul, Republic of Korea, 2019, pp. 1951–1960.
Crossref Google Scholar
[38]
M. Alizadeh, J. Fernández-Marqués, N. D. Lane, and Y. Gal, An empirical study of binary neural networks’ optimization, presented at 7th International Conference on Learning Representations, New Orleans, LA, USA, 2018.
Google Scholar
[39]
Hou L., Yao Q., and Kwok J. T., Loss-aware binarization of   deep networks, arXiv preprint arXiv: 1611.01600, 2016.
Google Scholar
[40]
K. Helwegen, J. Widdicombe, L. Geiger, Z. Liu, K. -T. Cheng, and R. Nusselder, Latent weights do not exist: Rethinking binarized neural network optimization, in Proc. Advances in Neural Information Processing Systems, Vancouver, Canada, 2019, pp. 7531–7542.
Google Scholar
[41]
T. Simons and D. -J. Lee, A review of binarized neural networks, Electronics, vol. 8, no. 6, p. 661, 2019.
Crossref Google Scholar
[42]
H. Qin, R. Gong, X. Liu, X. Bai, J. Song, and N. Sebe, Binary neural networks: A survey, Pattern Recognition, vol. 105, p. 107281, 2020.
Crossref Google Scholar
[43]
K. Swersky, D. Duvenaud, J. Snoek, F. Hutter, and M. A. Osborne, Raiders of the lost architecture: Kernels for bayesian optimization in conditional parameter spaces, arXiv preprint arXiv: 1409.4011, 2014.
Google Scholar
[44]
K. Kandasamy, W. Neiswanger, J. Schneider, B. Poczos, and E. Xing, Neural architecture search with Bayesian optimisation and optimal transport, arXiv preprint arXiv: 1802.07191, 2018.
Google Scholar
[45]
E. Real, S. Moore, A. Selle, S. Saxena, Y. L. Suematsu, J. Tan, Q. V. Le, and A. Kurakin, Large-scale evolution of image classifiers, in Proc. 34th International Conference on Machine Learning, Sydney, Australia, 2017, pp. 2902–2911.
Google Scholar
[46]
T. Elsken, J. H. Metzen, and F. Hutter, Efficient multi-objective neural architecture search via Lamarckian evolution, arXiv preprint arXiv: 1804.09081, 2018.
Google Scholar
[47]
E. Real, A. Aggarwal, Y. Huang, and Q. V. Le, Aging evolution for image classifier architecture search, presented at AAAI Conference on Artificial Intelligence, Honolulu, HI, USA, 2019.
Crossref
[48]
B. Baker, O. Gupta, N. Naik, and R. Raskar, Designing neural network architectures using reinforcement learning, arXiv preprint arXiv: 1611.02167, 2016.
Google Scholar
[49]
Z. Zhong, J. Yan, W. Wu, J. Shao, and C. -L. Liu, Practical block-wise neural network architecture generation, in Proc. 2018 IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 2018, pp. 2423–2432.
Crossref Google Scholar
[50]
B. Zoph and Q. V. Le, Neural architecture search with reinforcement learning, arXiv preprint arXiv: 1611.01578, 2016.
Google Scholar
[51]
S. Xie, H. Zheng, C. Liu, and L. Lin, SNAS: Stochastic neural architecture search, arXiv preprint arXiv: 1812.09926, 2018.
Google Scholar
[52]
H. Cai, L. Zhu, and S. Han, ProxylessNAS: Direct neural architecture search on target task and hardware, arXiv preprint arXiv: 1812.00332, 2018.
Google Scholar
Tsinghua Science and Technology
Volume 28 Issue 1,
February 2023
Pages 207-220
DOI: 10.26599/TST.2021.9010084
Cite this article:
Li Y, Geng T, Stein S, et al. GAAF: Searching Activation Functions for Binary Neural Networks Through Genetic Algorithm. Tsinghua Science and Technology, 2023, 28(1): 207-220. https://doi.org/10.26599/TST.2021.9010084

722

Views

39

Downloads

7

Crossref

2

Web of Science

8

Scopus

0

CSCD

Altmetrics
Received: 15 October 2021
Accepted: 01 November 2021
Published: 21 July 2022
© The author(s) 2023.

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Return