Abstract
Restricted Boltzmann Machines (RBM) have been widely applied in image processing. For RBM-based models on image recognition and image generation tasks, extracting expressive real-valued features and alleviating the overfitting problem are extremely important. In this paper, we propose a Gaussian Restricted Boltzmann Machine with binary Auxiliary units (GARBM), which designs binary auxiliary units in its visible layer and constructs parameterized real-valued features in its hidden layer. Specifically, based on the designed energy function in GARBM, activated auxiliary units are directly used to control probabilities of visible units and hidden units to extract real-valued features. Moreover, auxiliary units and their resulting feature selection mechanism not only alleviate the “gradient-variance” problem, but also provide certain randomness to other units to alleviate overfitting without introducing more hyperparameters. To build more effective deep models, we propose GARBM-based deep neural networks, and the effectiveness of proposed neural networks is verified in experiments.
Similar content being viewed by others
References
Lopez R, Regier J, Jordan M et al (2019) Information constraints on auto-encoding variational Bayes. Adv Neural Inf Process Syst 2019
Yan Q, Wang M, Huang W et al (2019) Automatically synthesizing DoS attack traces using generative adversarial networks. Int J Mach Learn Cybern 10(12):3387–3396
Kuleshov V, Ermon S (2017) Neural variational inference and learning in undirected graphical models. Adv Neural Inf Process Syst
Wang X, Zhao Y, Pourpanah F (2020) Recent advances in deep learning. Int J Mach Learn Cybern 11(11):747–750
Srivastava N, Hinton G, Krizhevsky A et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958
Blundell C, Cornebise J, Kavukcuoglu K (2015) Weight uncertainty in neural networks. In: International conference on machine learning
Zhang N, Ding S, Zhang J et al (2017) Research on point-wise gated deep networks. Appl Soft Comput 52:1210–1221
Ranzato M, Krizhevsky A, Hinton GE (2010) Factored 3-Way restricted Boltzmann machines for modeling natural images. J Mach Learn Res 9:621–628
Courville A, Desjardins G, Bergstra J et al (2014) The spike-and-slab RBM and extensions to discrete and sparse data distributions. IEEE Trans Pattern Anal Mach Intell 36(9):1874–1887
Ding S, Zhang N, Zhang J et al (2017) Unsupervised extreme learning machinewith representational features. Int J Mach Learn Cybern 8(2):587–595
Zhai J, Zhou X, Zhang S et al (2019) Ensemble RBM-based classifier using fuzzy integral for big data classification. Int J Mach Learn Cybern 10:3327–3337
Wen Y, Erick D (2019) Deep Boltzmann machine for nonlinear system modelling. Int J Mach Learn Cybern 10:1705–1716
Schmitt J, Roth S (2021) Sampling-free variational inference for neural networks with multiplicative activation noise. arXiv:2103.08497
Mescheder L, Nowozin S, Geiger A (2017) Adversarial variational Bayes: unifying variational autoencoders and generative adversarial networks. In: International conference on machine learning
Tolstikhin I, Bousquet O, Gelly S, et al (2017) Wasserstein Auto-Encoders. arXiv:1711.01558, arXiv, 2017
Felhi G, Leroux J, Seddah D (2020) Controlling the interaction between generation and inference in semi-supervised variational autoencoders using importance weighting. arXiv:2010.06549.
Vahdat A, Macready W G, Bian Z, et al (2018) DVAE++: discrete variational autoencoders with overlapping transformations. In: International conference on machine learning
Nair V, Hinton GE (2010) Rectified linear units improve restricted Boltzmann machines. In: International conference on international conference on machine learning
Su Q, Liao X, Li C et al (2017) Unsupervised learning with truncated gaussian graphical models. In: AAAI conference on artificial intelligence
Cho K, Raiko T, Ilin A (2014) Gaussian-Bernoulli deep Boltzmann machine. In: IEEE international joint conference on neural networks
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: International conference of learning representation (oral)
Acknowledgements
This work is supported by the National Natural Science Foundations of China (Nos. 61976216 and 61672522).
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
Zhang, J., Ding, S., Sun, T. et al. A Gaussian RBM with binary auxiliary units. Int. J. Mach. Learn. & Cyber. 13, 2425–2433 (2022). https://doi.org/10.1007/s13042-022-01534-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13042-022-01534-6