Abstract
Automated neural architecture search (NAS) methods are now employed to routinely deliver high-quality neural network architectures for various challenging data sets and reduce the designer’s effort. The NAS methods utilizing multi-objective evolutionary algorithms are especially useful when the objective is not only to minimize the network error but also to reduce the number of parameters (weights) or power consumption of the inference phase. We propose a multi-objective NAS method based on Cartesian genetic programming for evolving convolutional neural networks (CNN). The method allows approximate operations to be used in CNNs to reduce the power consumption of a target hardware implementation. During the NAS process, a suitable CNN architecture is evolved together with selecting approximate multipliers to deliver the best trade-offs between accuracy, network size, and power consumption. The most suitable 8 × N-bit approximate multipliers are automatically selected from a library of approximate multipliers. Evolved CNNs are compared with CNNs developed by other NAS methods on the CIFAR-10 and SVHN benchmark problems.
Similar content being viewed by others
References
I. Goodfellow, Y. Bengio, A. Courville, Deep Learning (MIT Press, New York, 2016)
V. Sze, Y. Chen, T. Yang, J.S. Emer, Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017)
S. Mittal, A survey of techniques for approximate computing. ACM Comput. Surv. 48(4), 1–33 (2016)
P. Panda, A. Sengupta, S.S. Sarwar, G. Srinivasan, S. Venkataramani, A. Raghunathan, K. Roy, Invited—cross-layer approximations for neuromorphic computing: From devices to circuits and systems. In: 53nd Design Automation Conference, pp. 1–6. IEEE (2016). https://doi.org/10.1145/2897937.2905009
S. Venkataramani et al., Efficient AI system design with cross-layer approximate computing. Proc. IEEE 108(12), 2232–2250 (2020). https://doi.org/10.1109/JPROC.2020.3029453
T. Elsken, J.H. Metzen, F. Hutter, Neural architecture search: a survey. J. Mach. Learn. Res. 20(55), 1–21 (2019)
P. Ren, Y. Xiao, X. Chang, P.Y. Huang, Z. Li, X. Chen, X. Wang, A comprehensive survey of neural architecture search: challenges and solutions. ACM Comput. Surv. 54, 4 (2021). https://doi.org/10.1145/3447582
B. Zoph, Q.V. Le, Neural architecture search with reinforcement learning (2016). http://arxiv.org/abs/1611.01578
X. Yao, Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)
Z. Lu, I. Whalen, V. Boddeti, Y.D. Dhebar, K. Deb, E.D. Goodman, W. Banzhaf, NSGA-Net: neural architecture search using multi-objective genetic algorithm. In: Proceedings of the Genetic and Evolutionary Computation Conference, pp. 419–427. ACM (2019)
K.O. Stanley, J. Clune, J. Lehman, R. Miikkulainen, Designing neural networks through neuroevolution. Nat. Mach. Intell. 1, 24–35 (2019)
H. Cai, C. Gan, T. Wang, Z. Zhang, S. Han, Once-for-all: Train one network and specialize it for efficient deployment. In: International Conference on Learning Representations (2020)
H. Cai, L. Zhu, S. Han, ProxylessNAS: Direct neural architecture search on target task and hardware. In: International Conference on Learning Representations (2019)
L. Sekanina, Neural architecture search and hardware accelerator co-search: a survey. IEEE Access 9, 151337–151362 (2021). https://doi.org/10.1109/ACCESS.2021.3126685
V. Mrazek, L. Sekanina, Z. Vasicek, Libraries of approximate circuits: Automated design and application in CNN accelerators. IEEE J. Emerg. Sel. Topics Circuits Syst. 10(4), 406–418 (2020). https://doi.org/10.1109/JETCAS.2020.3032495
S.S. Sarwar, S. Venkataramani, A. Ankit, A. Raghunathan, K. Roy, Energy-efficient neural computing with approximate multipliers. J. Emerg. Technol. Comput. Syst. 14(2), 1–23 (2018)
M. Pinos, V. Mrazek, L. Sekanina, Evolutionary neural architecture search supporting approximate multipliers. In: Genetic Programming—24th European Conference, EuroGP 2021, LNCS, vol. 12691, pp. 82–97. Springer (2021). https://doi.org/10.1007/978-3-030-72812-0_6
V. Mrazek, R. Hrbacek, et al., Evoapprox8b: Library of approximate adders and multipliers for circuit design and benchmarking of approximation methods. In: Proceedings of DATE’17, pp. 258–261 (2017)
M. Abadi, A. Agarwal, et al., TensorFlow: Large-scale machine learning on heterogeneous systems (2015). https://www.tensorflow.org/. Software available from tensorflow.org
F. Vaverka, V. Mrazek, Z. Vasicek, L. Sekanina, TFApprox: Towards a Fast Emulation of DNN Approximate Hardware Accelerators on GPU. In: Design, Automation and Test in Europe, pp. 1–4 (2020)
V. Mrazek, Z. Vasicek, L. Sekanina, A.M. Hanif, M. Shafique, ALWANN: Automatic layer-wise approximation of deep neural network accelerators without retraining. In: Proceedings of the IEEE/ACM International Conference on Computer-Aided Design, pp. 1–8. IEEE (2019)
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition. CoRR abs/1512.03385 (2015). http://arxiv.org/abs/1512.03385
Intel Movidius vision processing units (VPUs) (2021). https://www.intel.com/content/www/us/en/products/details/processors/movidius-vpu.html
Y. Chen, T. Luo, S. Liu, S. Zhang, L. He, J. Wang, L. Li, T. Chen, Z. Xu, N. Sun, O. Temam, DaDianNao: a machine-learning supercomputer. In: 2014 47th Annual IEEE/ACM International Symposium on Microarchitecture, pp. 609–622 (2014). https://doi.org/10.1109/MICRO.2014.58
Y. Chen, T. Yang, J. Emer, V. Sze, Eyeriss v2: a flexible accelerator for emerging deep neural networks on mobile devices. IEEE J. Emerg. Select. Topics Circuits Syst. 9(2), 292–308 (2019)
N.P. Jouppi, C. Young, N. Patil, D. Patterson, A domain-specific architecture for deep neural networks. Commun. ACM 61(9), 50–59 (2018)
S. Mittal, A survey of FPGA-based accelerators for convolutional neural networks. Neural Comput. Appl. 32(32), 1109–1139 (2020)
A. Garofalo, G. Tagliavini, F. Conti, D. Rossi, L. Benini, Xpulpnn: accelerating quantized neural networks on RISC-V processors through ISA extensions. In: 2020 Design, Automation Test in Europe Conference Exhibition (DATE), pp. 186–191 (2020). https://doi.org/10.23919/DATE48585.2020.9116529
E. Wang, J.J. Davis, R. Zhao, H.C. Ng, X. Niu, W. Luk, P.Y.K. Cheung, G.A. Constantinides, Deep neural network approximation for custom hardware: where we’ve been, where we’re going. ACM Comput. Surv. 52, 2 (2019). https://doi.org/10.1145/3309551
W. Jiang, L. Yang, S. Dasgupta, J. Hu, Y. Shi, Standing on the shoulders of giants: hardware and neural architecture co-search with hot start (2020). https://arxiv.org/abs/2007.09087
P. Gysel, J. Pimentel, M. Motamedi, S. Ghiasi, Ristretto: a framework for empirical study of resource-efficient inference in convolutional neural networks. IEEE Trans. Neural Netw. Learn. Syst. 29(11), 5784–5789 (2018)
K.O. Stanley, R. Miikkulainen, Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)
E. Real, S. Moore, A. Selle, S. Saxena, Y.L. Suematsu, J. Tan, Q. Le, A. Kurakin, Large-Scale Evolution of Image Classifiers. arXiv e-prints arXiv:1703.01041 (2017)
M. Suganuma, S. Shirakawa, T. Nagao, A genetic programming approach to designing convolutional neural network architectures. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO ’17, pp. 497–504. ACM (2017)
Z. Lu, K. Deb, E.Goodman, W. Banzhaf, V.N. Boddeti, NSGANetV2: Evolutionary multi-objective surrogate-assisted neural architecture search. In: Computer Vision—ECCV 2020, pp. 35–51. Springer, Cham (2020)
K. Deb, A. Pratap, S. Agarwal, T. Meyarivan, A fast and elitist multiobjective genetic algorithm: NSGA-II. IEEE Trans. Evol. Comput. 6(2), 182–197 (2002)
Q. Lu, W. Jiang, X. Xu, Y. Shi, J. Hu, On neural architecture search for resource-constrained hardware platforms (2019). http://arxiv.org/abs/1911.00105
Y. Lin, M. Yang, S. Han, NAAS: Neural accelerator architecture search. In: 2021 58th ACM/ESDA/IEEE Design Automation Conference (DAC) (2021)
J.F. Miller, Cartesian Genetic Programming (Springer, Berlin, 2011)
K. He, X. Zhang, S. Ren, J. Sun, Identity mappings in deep residual networks. In: Computer Vision—ECCV 2016, pp. 630–645. Springer (2016)
T. Devries, G.W. Taylor, Improved regularization of convolutional neural networks with cutout. CoRR abs/1708.04552 (2017). http://arxiv.org/abs/1708.04552
C. Shorten, T. Khoshgoftaar, A survey on image data augmentation for deep learning. J. Big Data 6, 1–48 (2019)
, A. Krizhevsky, V. Nair, G. Hinton, CIFAR-10 (Canadian Institute for Advanced Research) http://www.cs.toronto.edu/~kriz/cifar.html
Y. Netzer, T. Wang, A. Coates, A. Bissacco, B. Wu, A.Y. Ng, Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011 (2011). http://ufldl.stanford.edu/housenumbers/nips2011_housenumbers.pdf
M. Fleischer, The measure of pareto optima applications to multi-objective metaheuristics, in Evolutionary Multi-criterion Optimization. (Springer, Berlin, 2003), pp. 519–533
W. Jiang, L. Yang, E.H.M. Sha, Q. Zhuge, S. Gu, S. Dasgupta, Y. Shi, J. Hu, Hardware/software co-exploration of neural architectures. IEEE Trans. Comput.-Aid. Des. Integr. Circuits Syst. 39(12), 4805–4815 (2020). https://doi.org/10.1109/TCAD.2020.2986127
M. Loni, S. Sinaei, A. Zoljodi, M. Daneshtalab, M. Sjödin, DeepMaker: a multi-objective optimization framework for deep neural networks in embedded systems. Microprocess. Microsyst. 73, 102989 (2020). https://doi.org/10.1016/j.micpro.2020.102989
P. Achararit, M.A. Hanif, R.V.W. Putra, M. Shafique, Y. Hara-Azumi, APNAS: accuracy-and-performance-aware neural architecture search for neural hardware accelerators. IEEE Access 8, 165319–165334 (2020). https://doi.org/10.1109/ACCESS.2020.3022327
Y. Jiang, X. Wang, W. Zhu, Hardware-aware transformable architecture search with efficient search space. In: 2020 IEEE International Conference on Multimedia and Expo (ICME), pp. 1–6 (2020). https://doi.org/10.1109/ICME46284.2020.9102721
T. Elsken, J.H. Metzen, F. Hutter, Efficient multi-objective neural architecture search via Lamarckian evolution. In: 7th International Conference on Learning Representations, ICLR 2019. OpenReview.net (2019)
B. Zoph, V. Vasudevan, J. Shlens, Q.V. Le, Learning transferable architectures for scalable image recognition. In: 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 8697–8710 (2018). https://doi.org/10.1109/CVPR.2018.00907
M. Wistuba, A. Rawat, T. Pedapati, A survey on neural architecture search. CoRR abs/1905.01392 (2019). http://arxiv.org/abs/1905.01392
H. Tann, S. Hashemi, S. Reda, Lightweight Deep Neural Network Accelerators Using Approximate SW/HW Techniques (Springer, Berlin, 2019), pp. 289–305
H. Lee, E. Hyung, S.J. Hwang, Rapid neural architecture search by learning to generate graphs from datasets. In: International Conference on Learning Representations (2021). https://openreview.net/forum?id=rkQuFUmUOg3
Z. Lu, G. Sreekumar, E. Goodman, W. Banzhaf, K. Deb, V.N. Boddeti, Neural architecture transfer. IEEE Trans. Pattern Anal. Mach. Intell. 43(9), 2971–2989 (2021). https://doi.org/10.1109/TPAMI.2021.3052758
Acknowledgements
This work was supported by the Czech Science Foundation Project 21-13001S. The computational experiments were supported by The Ministry of Education, Youth and Sports from the Large Infrastructures for Research, Experimental Development and Innovations project “e-Infrastructure CZ - LM2018140”.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Pinos, M., Mrazek, V. & Sekanina, L. Evolutionary approximation and neural architecture search. Genet Program Evolvable Mach 23, 351–374 (2022). https://doi.org/10.1007/s10710-022-09441-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10710-022-09441-z