Abstract
Training of deep neural networks is difficult due to vanishing gradients. Therefore, a pre-training procedure based on restricted Boltzmann machines is suggested to resolve this problem. However, new developments in deep learning aim to resolve the problem with vanishing gradients by using rectifier linear units (ReLU). This study compares the performance of a RBM pre-trained auto-encoder with sigmoid activations to the performance of auto-encoder with ReLU activation. The results showed that the ReLU auto-encoder achieved better reconstruction and saved training time, since it doesn't require pre-training .
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kramer, M.A.: Nonlinear principal component analysis using autoassociative neural networks. AIChE J. 37, 233–243 (1991)
Hochreiter, S., Bengio, Y., Frasconi, P., Schmidhuber, J.: Gradient flow in recurrent nets: the difficulty of learning long-term dependencies, a field guide to dynamical recurrent neural networks. IEEE Press (2001)
Hinton, G.E. Salakhutdinov, R.R.: Reducing the dimensionality of data with neural networks. Sci. 313, 504–507 (2006)
Hinton, G.E., Osindero, S., Teh, Y.-W.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)
Haykin, S.S.: Neural Networks and Learning Machines/Simon Haykin. Prentice Hall, New York (2009)
Smolensky, P.: Information Processing in Dynamical Systems: Foundations of Harmony Theory (1986)
Jaitly, N., Hinton, G.: Learning a better representation of speech soundwaves using restricted boltzmann machines. In: 2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (2011)
Sailor, H.B., Agrawal, D.M., Patil, H.A.: Unsupervised filterbank learning using convolutional restricted boltzmann machine for environmental sound classification. InterSpeech (2017)
Yang, J., Deng, J., Li, S., Hao, Y.: Improved traffic detection with support vector machine based on restricted Boltzmann machine. Soft. Comput. 21(11), 3101–3112 (2015). https://doi.org/10.1007/s00500-015-1994-9
Vrábel, J., Pořı́zka, P., Kaiser, J.: Restricted Boltzmann machine method for dimensionality reduction of large spectroscopic data. Spectrochim. Acta Part B At. Spectrosc. 167, 105849 (2020)
Zhang, Y., Peng, P., Liu, C., Zhang, H.: Anomaly detection for industry product quality inspection based on Gaussian restricted Boltzmann machine. In: 2019 IEEE International Conference on Systems, Man and Cybernetics (SMC) (2019)
Tan, C.C., Eswaran, C.: Performance comparison of three types of autoencoder neural networks. In: 2008 Second Asia International Conference on Modelling & Simulation (AMS) (2008)
Nuha, H., Mohandes, M., Liu, B.: Seismic data compression using auto-associative neural network and restricted Boltzmann machine. In: SEG Technical Program Expanded Abstracts 2018, pp. 186–190. Society of Exploration Geophysicists (2018)
Pumsirirat, A., Yan, L.: Credit card fraud detection using deep learning based on auto-encoder and restricted boltzmann machine. Int. J. Adv. Comput. Sci. Appl. 9, 18–25 (2018)
He, D., et al.: Intrusion detection based on stacked autoencoder for connected healthcare systems. IEEE Netw. 33, 64–69 (2019)
Mahmoud, A.M., Alrowais, F., Karamti, H.: A hybrid deep contractive autoencoder and restricted boltzmann machine approach to differentiate representation of female brain disorder. Procedia Comput. Sci. 176, 1033–1042 (2020)
Li, J., Yu, Z.L., Gu, Z., Wu, W., Li, Y., Jin, L.: A hybrid network for ERP detection and analysis based on restricted Boltzmann machine. IEEE Trans. Neural Syst. Rehabil. Eng. 26, 563–572 (2018)
Kuremoto, T., Kimura, S., Kobayashi, K., Obayashi, M.: Time series forecasting using restricted boltzmann machine. In: International Conference on Intelligent Computing (2012)
Qiao, J., Wang, L.: Nonlinear system modeling and application based on restricted Boltzmann machine and improved BP neural network. Appl. Intell. 51(1), 37–50 (2020). https://doi.org/10.1007/s10489-019-01614-1
Ma, M., Sun, C., Chen, X.: Deep coupling autoencoder for fault diagnosis with multimodal sensory data. IEEE Trans. Industr. Inf. 14, 1137–1145 (2018)
Glorot, X., Bordes, A., Bengio, Y.: Deep sparse rectifier neural networks. In: Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics (2011)
Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (2010)
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., Chen, L.-C.: Mobilenetv2: inverted residuals and linear bottlenecks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)
Chollet, F.: Xception: deep learning with depthwise separable convolutions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017)
Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention (2015)
Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39, 2481–2495 (2017)
Zhou, Y., Arpit, D., Nwogu, I., Govindaraju, V.: Is joint training better for deep auto-encoders? (2014)
Krizhevsky, A., Hinton, G.: Learning multiple layers of features from tiny images (2009)
Acknowledgement
The experiments described in this paper became possible thanks to the computing resources and technical support provided by UNITe project: https://unite-bg.eu/.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Boyadzhiev, T., Dimitrova, S., Tsvetanov, S. (2022). Comparison of Auto-Encoder Training Algorithms. In: Ahram, T., Taiar, R. (eds) Human Interaction, Emerging Technologies and Future Systems V. IHIET 2021. Lecture Notes in Networks and Systems, vol 319. Springer, Cham. https://doi.org/10.1007/978-3-030-85540-6_88
Download citation
DOI: https://doi.org/10.1007/978-3-030-85540-6_88
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-85539-0
Online ISBN: 978-3-030-85540-6
eBook Packages: EngineeringEngineering (R0)