Advertisement

Optimizing Convolutional Neural Networks for Embedded Systems by Means of Neuroevolution

  • Filip Badan
  • Lukas SekaninaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11934)

Abstract

Automated design methods for convolutional neural networks (CNNs) have recently been developed in order to increase the design productivity. We propose a neuroevolution method capable of evolving and optimizing CNNs with respect to the classification error and CNN complexity (expressed as the number of tunable CNN parameters), in which the inference phase can partly be executed using fixed point operations to further reduce power consumption. Experimental results are obtained with TinyDNN framework and presented using two common image classification benchmark problems – MNIST and CIFAR-10.

Keywords

Evolutionary Algorithm Convolutional neural network Neuroevolution Embedded Systems Energy Efficiency 

Notes

Acknowledgments

This work was supported by the Ministry of Education, Youth and Sports, under the INTER-COST project LTC 18053, NPU II project IT4Innovations excellence in science LQ1602 and by Large Infrastructures for Research, Experimental Development and Innovations project “IT4Innovations National Supercomputing Center – LM2015070”.

References

  1. 1.
    Dong, J.-D., Cheng, A.-C., Juan, D.-C., Wei, W., Sun, M.: DPP-Net: device-aware progressive search for pareto-optimal neural architectures. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 540–555. Springer, Cham (2018).  https://doi.org/10.1007/978-3-030-01252-6_32CrossRefGoogle Scholar
  2. 2.
    Hashemi, S., Anthony, N., Tann, H., Bahar, R.I., Reda, S.: Understanding the impact of precision quantization on the accuracy and energy of neural networks. In: DATE, pp. 1478–1483. EDAA (2017)Google Scholar
  3. 3.
    Hsu, C., et al.: MONAS: multi-objective neural architecture search using reinforcement learning. CoRR abs/1806.10332 (2018). http://arxiv.org/abs/1806.10332
  4. 4.
    Krizhevsky, A., Sutskever, I., Hinton, G.E.: Imagenet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems 25, pp. 1097–1105. Curran Associates, Inc. (2012)Google Scholar
  5. 5.
    Miikkulainen, R., et al.: Evolving deep neural networks. CoRR abs/1703.00548 (2017). http://arxiv.org/abs/1703.00548
  6. 6.
    Nomi, T.: TinyDNN. https://github.com/tiny-dnn/tiny-dnn (2016)
  7. 7.
    Panda, P., et al.: Invited - cross-layer approximations for neuromorphic computing: from devices to circuits and systems. In: 53rd Design Automation Conference, pp. 1–6. IEEE (2016).  https://doi.org/10.1145/2897937.2905009
  8. 8.
    Real, E., et al.: Large-scale evolution of image classifiers. arXiv e-prints arXiv:1703.01041 (2017)
  9. 9.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)CrossRefGoogle Scholar
  10. 10.
    Suganuma, M., Shirakawa, S., Nagao, T.: A genetic programming approach to designing convolutional neural network architectures. In: Proceedings of the Genetic and Evolutionary Computation Conference, GECCO 2017, pp. 497–504. ACM (2017)Google Scholar
  11. 11.
    Sze, V., Chen, Y., Yang, T., Emer, J.S.: Efficient processing of deep neural networks: a tutorial and survey. Proc. IEEE 105(12), 2295–2329 (2017)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Faculty of Information Technology IT4Innovations Centre of ExcellenceBrno University of TechnologyBrnoCzech Republic

Personalised recommendations