Abstract
Monte Carlo dropout sampling (MC Dropout), which approximates a Bayesian Neural Network, is useful for measuring the uncertainty in the output of a Deep Neural Network (DNN). However, because it takes a long time to sample DNN’s output for calculating its distribution, it is difficult to apply it to edge computing where resources are limited. Thus, this research proposes a method of reducing a sampling time required for MC Dropout in edge computing by parallelizing the calculation circuit using FPGA. To apply MC dropout in an FPGA, this paper shows an efficient implementation by binarizing the neural network and simplifying dropout computation by pre-dropout and localizing parallel circuits. The proposed method was evaluated using the MNIST dataset and a dataset of satellite images of ships at sea captured. As a result, it was possible to reject approximately 60% of data which the model had not learned as “uncertain” on a classification identification problem of the image on an FPGA. Furthermore, for 20 units in parallel, the amount of increase in the circuit scale was only 2–3 times that of non-parallelized circuits. In terms of inference speed, parallelization of dropout circuits has achieved up to 3.62 times faster.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Feng, D., Rosenbaum, L., Dietmayer, K.: Towards safe autonomous driving: capture uncertainty in the deep neural network for Lidar 3D vehicle detection. In: 2018 21st International Conference on Intelligent Transportation Systems (ITSC) (2018). https://doi.org/10.1109/itsc.2018.8569814
Gal, Y., Ghahramani, Z.: Bayesian convolutional neural networks with Bernoulli approximate variational inference. In: 4th International Conference on Learning Representations (ICLR) Workshop Track (2016)
Gal, Y., Ghahramani, Z.: Dropout as a Bayesian approximation: representing model uncertainty in deep learning. In: Proceedings of the 33rd International Conference on International Conference on Machine Learning, ICML 2016, vol. 48, pp. 1050–1059. JMLR.org (2016)
Hashimoto, S., Sugimoto, Y., Hamamoto, K., Ishihama, N.: Ship classification from SAR images based on deep learning. In: Arai, K., Kapoor, S., Bhatia, R. (eds.) Intell. Syst. Appl., vol. 868, pp. 18–34. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-01054-6_2
Kendall, A., Gal, Y.: What uncertainties do we need in Bayesian deep learning for computer vision? pp. 5574–5584. Curran Associates, Inc. (2017)
Miller, D., Dayoub, F., Milford, M., Sünderhauf, N.: Evaluating merging strategies for sampling-based uncertainty techniques in object detection. arXiv:1809.06006 [cs.CV] (2018)
Myojin, T., Hashimoto, S., Mori, K., Sugawara, K., Ishihama, N.: Improving reliability of object detection for lunar craters using Monte Carlo dropout. In: Tetko, I.V., Kůrková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11729, pp. 68–80. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30508-6_6
Takamaeda, S.: NNgen/nngen (February 2020). https://github.com/NNgen/nngen
Umuroglu, Y., et al.: FINN: a framework for fast, scalable binarized neural network inference. In: Proceedings of the 2017 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays, FPGA 2017, pp. 65–74. Association for Computing Machinery, New York, NY, USA (2017). https://doi.org/10/ggmnh6
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Myojin, T., Hashimoto, S., Ishihama, N. (2020). Detecting Uncertain BNN Outputs on FPGA Using Monte Carlo Dropout Sampling. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12397. Springer, Cham. https://doi.org/10.1007/978-3-030-61616-8_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-61616-8_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-61615-1
Online ISBN: 978-3-030-61616-8
eBook Packages: Computer ScienceComputer Science (R0)