Abstract
Deep neural network (DNN) has been applied in many fields and achieved great successes. However, DNN suffers from poor robustness for uncertainties because of its characteristic of the deterministic representation. To overcome this problem, a novel robust DNN (RDNN) is designed in this paper. First, a fuzzy denoising autoencoder (FDA) is developed to replace the general base-building unit in DNN. Then, the proposed RDNN is able to extract the robust representations to weaken the uncertainties. Second, a compact parameter strategy (CPS) is designed to reconstruct the parameters of FDA. Then, the computational burden of FDA can be alleviated to speed up the learning process. Third, an adaptive back-propagation (ABP) algorithm, with an adaptive learning rate strategy, is proposed to update the parameters of RDNN. Then, the performance of RDNN can be improved. Finally, the results on the benchmark problems and real applications demonstrate the effectiveness of RDNN.
Similar content being viewed by others
References
Athanasios, V., Nikolaos, D.: Deep learning for computer vision: a brief review. Comput. Intell. Neurosci. 49, 2329–2338 (2018)
Hinton, G., Deng, L., Dong, Y.: Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. IEEE Signal Process Mag. 29(6), 82–97 (2012)
Hwang, M., Wang, D., Jiang, W.C., Pan, X.: An adaptive regularization approach to colonoscopic polyp detection using a cascaded structure of encoder–decoders. Int. J. Fuzzy Syst. 21(7), 2091–2101 (2019)
Huang, W., Song, G., Hong, H., Xie, K.: Deep architecture for traffic flow prediction: deep belief networks with multitask learning. IEEE Trans. Intell. Transp. Syst. 15(5), 2191–2201 (2014)
Saad, E.W., Prokhorov, D.V., Wunsch, D.C.: Comparative study of stock trend prediction using time delay, recurrent and probabilistic neural networks. IEEE Trans. on Neural Netw. 9(6), 1456–1470 (1998)
Xu, Q.Y., Yang, Y.Q., Zhang, C.J., Zhang, L.: Deep convolutional neural network-based autonomous marine vehicle maneuver. Int. J. Fuzzy Syst. 20(2), 687–699 (2018)
Cheng, Y., Sun, Z.J., Huang, Y.X., Zhang, W.D.: Fuzzy categorical deep reinforcement learning of a defensive game for an unmanned surface vessel. Int. J. Fuzzy Syst. 21(2), 592–606 (2019)
Lin, F.J., Lin, C.H., Shen, P.H.: Self-constructing fuzzy neural network speed controller for permanent-magnet synchronous motor drive. IEEE Trans. Fuzzy Syst. 9(5), 751–759 (2001)
Hinton, G.E., Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Science 313(5786), 504–507 (2006)
Long, M., Wang, J., Cao, Y., Sun, J., Yu, P.S.: Deep learning of transferable representation for scalable domain adaptation. IEEE Trans. Knowl. Data Eng. 18(8), 2027–2040 (2016)
Hong, Y.G., Zhong, P.J.: Finite-time stabilization of nonlinear systems with parametric and dynamic uncertainties. IEEE Trans. Autom. Control 51(12), 1950–1956 (2006)
Wang, Y.C., Chien, C.J., Chi, R.H., Hou, Z.S.: A fuzzy-neural adaptive terminal iterative learning control for fed-batch fermentation processes. Int. J. Fuzzy Syst. 17(3), 423–433 (2015)
Jose, N., Josue, F., Victor, P.: Uncertainty weighting and propagation in DNN–HMM-based speech recognition. Comput. Speech Lang. 47, 30–46 (2018)
Kim, S.W., Yu, Z.B., Kil, R.M.: Deep learning of support vector machines with class probability output networks. Neural Netw. 64, 19–28 (2015)
Goldberger, Z.D., Walsh, K.E.: Syncope units: an emerging paradigm. Pace-Pacing and Clinical Electrophysiology 42(7), 828–829 (2019)
Han, B., Yao, Q.M., Yu, X.R.: Co-teaching robust training of deep neural networks with extremely noisy labels. Neural Inf. Processing Syst. 31, 345–364 (2018)
Zhou, Y.C., Liu, Y., Wang, R.: Training deep neural networks for image applications with complementary learning. J. Comput. Res. Dev. 54(12), 2649–2659 (2017)
Badiali, B., Titus, N.E.: Co-teaching: enhancing student learning through mentor-intern partnerships. IEEE Trans. Autom. Control 4(2), 74–80 (2014)
Srivastava, N., Hinton, G.E., Sutskever, I.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929–1958 (2014)
Frenay, B., Verleysen, M.: Classification in the presence of label noise: a survey. IEEE Trans. Neural Netw. Learn. Syst. 25(5), 845–869 (2014)
Kenzo, I., Takashi, I., Taichiro, S., Tomoyuki, T.: Deep shrinkage convolutional neural network for adaptive noise reduction. IEEE Signal Process. Lett. 25(2), 224–230 (2018)
Nie, D., Wang, L., Gao, Y.Z., Lian, J., Shen, D.: STRAINet: spatially varying stochastic residual adversarial networks for MRI pelvic organ segmentation. IEEE Trans. Neural Netw. Learn. Syst. 30, 5 (2019)
Wang, Q.L., Guo, W.B., Zhang, K.X.: Random feature nullification for adversary resistant deep architecture. Neural Netw. 70, 54–62 (2016)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. Comput. Vis. Pattern Recognit. 42(7), 770–778 (2016)
Battistone, F., Petrosino, A.: TGLSTM: a time based graph deep learning approach to gait recognition. Pattern Recogn. Lett. 24(4), 671–686 (2018)
Raja, K.B., Raghavendra, R., Vemuri, V.K., Busch, C.: Smartphone based visible iris recognition using deep sparse filtering. Comput. Vis. Pattern Recognit. 57, 33–42 (2015)
Jiang, W.Y., Chung, F.L., Qian, P.: Feedforward kernel neural networks, generalized least learning machine, and its deep learning with application to image classification. Appl. Soft Comput. 37, 125–141 (2015)
Azadeh, A., Ziaei, B., Moghaddam, M.: A hybrid fuzzy regression-fuzzy cognitive map algorithm for forecasting and optimization of housing market fluctuations. Expert Syst. Appl. 39, 298–315 (2012)
Han, H.G., Chen, Z.Y., Qiao, J.F.: A self-organizing interval Type-2 fuzzy-neural-network for modeling nonlinear systems. Neurocomputing 290(1), 196–207 (2018)
Huang, Y.P., Singh, A., Liu, S., Wu, S., Quoc, H., Sereter, A.: Developing transformed fuzzy neural networks to enhance medical data classification accuracy. Int. J. Fuzzy Syst. 20(6), 1925–1937 (2018)
Han, H.G., Liu, Z., Qiao, J.F.: Fuzzy-neural-network-based model predictive control for dissolved oxygen concentration of WWTPs. Int. J. Fuzzy Syst. 21(5), 1497–1510 (2019)
Han, H.G., Chen, Z.Y., Liu, H.X., Qiao, J.F.: A self-organizing interval type-2 fuzzy-neural-network for modeling nonlinear systems. Neurocomputing 290, 196–207 (2018)
Li, C.L., Chen, G.D., Sung, T.Y., Tsai, H.F.: Novel adaptive Kalman filter with fuzzy neural network for trajectory estimation system. Int. J. Fuzzy Syst. 21(6), 1649–1660 (2019)
Han, H.G., Liu, Z., Ge, L.M., Qiao, J.F.: Prediction of sludge bulking using the knowledge-leverage-based fuzzy neural network. Water Sci. Technol. 77(3), 617–627 (2018)
Deng, Y., Bao, F., Kong, Y.Y., Ren, Z.Q., Dai, Q.: Deep direct reinforcement learning for financial signal representation and trading. IEEE Trans. Neural Netw. Learn. Syst. 28(3), 653–664 (2017)
Deng, Y., Ren, Z.Q., Kong, Y.Y., Bao, F., Dai, Q.H.: A hierarchical fused fuzzy deep neural network for data classification. IEEE Trans. Fuzzy Syst. 25(4), 1006–1012 (2017)
Samui, S., Chakrabarti, I., Ghosh, S.: Time–frequency masking based supervised speech enhancement framework using fuzzy deep belief network. Appl. Soft Comput. 74, 583–602 (2019)
Khodayar, M., Kaynak, O., Khodayar, M.: Rough deep neural architecture for short-term wind speed forecasting. IEEE Trans. Industr. Inf. 13(6), 2770–2779 (2017)
Zheng, Y.J., Ling, H.F., Chen, S.Y., Xue, J.Y.: A hybrid neuro-fuzzy network based on differential biogeography-based optimization for online population classification in earthquakes. IEEE Trans. Fuzzy Syst. 23(4), 1070–1083 (2015)
Siderators, G., Ikonomopoulos, A., Hatziargryriou, N.D.: A novel fuzzy-based ensemble model for load forecasting using hybrid deep neural networks. Electr. Power Syst. Res. 178, 1–10 (2020)
Liang, W.Z., Zhao, G.Y., Zhao, J., Ma, C.: Hatziargryriou, Assessing the rockburst risk for deep shafts via distance-based multi-criteria decision making approaches with hesitant fuzzy information. Eng. Geol. 260, 524–536 (2019)
Bodyanskiy, Y., Tyshchenko, O.: A hybrid cascade neuro–fuzzy network with pools of extended neo–fuzzy neurons and its deep learning. Int. J. Appl. Math. Comput. Sci. 29(3), 477–488 (2019)
Ekpenyong, M., Etebong, P., Jackson, T.: A novel fuzzy-based convolutional neural network method to traffic flow prediction with uncertain traffic accident information. IEEE Access 7, 558–569 (2019)
Ricardo, D.A., Oliveira, L.I.: On the problem of forecasting air pollutant concentration with morphological models. Neurocomputing 265, 91–104 (2017)
Saverio, D.V., Grazia, F., Pardo, M.: Semi-supervised learning techniques in artificial olfaction: a novel approach to classification problems and drift counteraction. IEEE Sens. J. 12(11), 3215–3224 (2012)
Bezerra, E.C., Le, P.S., Braga, D.S.: A self-adaptive approach for particle swarm optimization applied to wind speed forecasting. J. Control Automat. Electr. Syst. 28(6), 785–795 (2017)
Gu, J.R., Zhu, M.C., Jiang, L.G.: Housing price forecasting based on genetic algorithm and support vector machine. Expert Syst. Appl. 38, 3383–3386 (2014)
Bork, L., Moller, S.: Forecasting house prices using dynamic model averaging and dynamic model selection. Int. J. Forecast. 31, 63–78 (2015)
Acknowledgements
This work was supported by National Key Research and Development Project under Grants 2018YFC1900800-5, National Science Foundation of China under Grants 61890930-5, 61622301 and 61903010, and Beijing Outstanding Young Scientist Program under Grant BJJWZYJH01201910005020. Asterisk indicates corresponding author
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Han, HG., Zhang, HJ. & Qiao, JF. Robust Deep Neural Network Using Fuzzy Denoising Autoencoder. Int. J. Fuzzy Syst. 22, 1356–1375 (2020). https://doi.org/10.1007/s40815-020-00845-6
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s40815-020-00845-6